< Prev | Home | Model | Random | Next >

Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 40 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')



Text #0

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2576. Min Act: -0.0001

Data Index: 1058142 (The Pile)

Max Activating Token Index: 503

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2449. Min Act: -0.0001

Data Index: 1061789 (The Pile)

Max Activating Token Index: 645

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2570. Min Act: -0.0001

Data Index: 1847439 (The Pile)

Max Activating Token Index: 365

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2297. Min Act: -0.0001

Data Index: 1482704 (The Pile)

Max Activating Token Index: 903

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2287. Min Act: -0.0001

Data Index: 1302106 (The Pile)

Max Activating Token Index: 691

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2356. Min Act: -0.0001

Data Index: 470042 (The Pile)

Max Activating Token Index: 242

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2607. Min Act: -0.0001

Data Index: 1326160 (The Pile)

Max Activating Token Index: 840

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2251. Min Act: -0.0001

Data Index: 1913735 (The Pile)

Max Activating Token Index: 539

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2386. Min Act: -0.0001

Data Index: 721728 (The Pile)

Max Activating Token Index: 545

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2190. Min Act: -0.0001

Data Index: 1562683 (The Pile)

Max Activating Token Index: 763

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.1976. Min Act: -0.0001

Data Index: 1429633 (The Pile)

Max Activating Token Index: 689

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2215. Min Act: -0.0001

Data Index: 1768406 (The Pile)

Max Activating Token Index: 659

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2122. Min Act: -0.0001

Data Index: 395119 (The Pile)

Max Activating Token Index: 675

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2159. Min Act: -0.0001

Data Index: 1122319 (The Pile)

Max Activating Token Index: 322

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2075. Min Act: -0.0001

Data Index: 551632 (The Pile)

Max Activating Token Index: 558

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.1961. Min Act: -0.0001

Data Index: 1958060 (The Pile)

Max Activating Token Index: 724

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2122. Min Act: -0.0001

Data Index: 1742209 (The Pile)

Max Activating Token Index: 530

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2079. Min Act: -0.0001

Data Index: 1459317 (The Pile)

Max Activating Token Index: 147

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.1954. Min Act: -0.0001

Data Index: 1546966 (The Pile)

Max Activating Token Index: 765

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2085. Min Act: -0.0001

Data Index: 328167 (The Pile)

Max Activating Token Index: 482

Click toggle to see full text

Truncated

Full Text #19