< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 9 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: 1.4846. Min Range: -1.4846

Max Act: 1.4328. Min Act: -0.0001

Data Index: 203653 (The Pile)

Max Activating Token Index: 402

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.4846. Min Range: -1.4846

Max Act: 1.3390. Min Act: -0.0001

Data Index: 480655 (The Pile)

Max Activating Token Index: 819

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.4846. Min Range: -1.4846

Max Act: 1.4846. Min Act: -0.0001

Data Index: 220299 (The Pile)

Max Activating Token Index: 705

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.4846. Min Range: -1.4846

Max Act: 1.3417. Min Act: -0.0001

Data Index: 1634956 (The Pile)

Max Activating Token Index: 306

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.4846. Min Range: -1.4846

Max Act: 1.3831. Min Act: -0.0001

Data Index: 1202061 (The Pile)

Max Activating Token Index: 513

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.4846. Min Range: -1.4846

Max Act: 1.2588. Min Act: -0.0001

Data Index: 1269887 (The Pile)

Max Activating Token Index: 334

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.4846. Min Range: -1.4846

Max Act: 1.3666. Min Act: -0.0001

Data Index: 1213293 (The Pile)

Max Activating Token Index: 646

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.4846. Min Range: -1.4846

Max Act: 1.1477. Min Act: -0.0001

Data Index: 1139947 (The Pile)

Max Activating Token Index: 803

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.4846. Min Range: -1.4846

Max Act: 1.1401. Min Act: -0.0001

Data Index: 1422047 (The Pile)

Max Activating Token Index: 719

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.4846. Min Range: -1.4846

Max Act: 1.2754. Min Act: -0.0001

Data Index: 719578 (The Pile)

Max Activating Token Index: 713

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.4846. Min Range: -1.4846

Max Act: 1.1210. Min Act: -0.0001

Data Index: 963074 (The Pile)

Max Activating Token Index: 36

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.4846. Min Range: -1.4846

Max Act: 1.2325. Min Act: -0.0001

Data Index: 1666972 (The Pile)

Max Activating Token Index: 581

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.4846. Min Range: -1.4846

Max Act: 1.1571. Min Act: -0.0001

Data Index: 1164958 (The Pile)

Max Activating Token Index: 592

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.4846. Min Range: -1.4846

Max Act: 1.1312. Min Act: -0.0001

Data Index: 1470346 (The Pile)

Max Activating Token Index: 690

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.4846. Min Range: -1.4846

Max Act: 1.1496. Min Act: -0.0001

Data Index: 1242099 (The Pile)

Max Activating Token Index: 292

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.4846. Min Range: -1.4846

Max Act: 1.0745. Min Act: -0.0001

Data Index: 126572 (The Pile)

Max Activating Token Index: 799

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.4846. Min Range: -1.4846

Max Act: 1.1789. Min Act: -0.0001

Data Index: 1531685 (The Pile)

Max Activating Token Index: 306

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.4846. Min Range: -1.4846

Max Act: 1.0269. Min Act: -0.0001

Data Index: 166449 (The Pile)

Max Activating Token Index: 111

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.4846. Min Range: -1.4846

Max Act: 1.1018. Min Act: -0.0001

Data Index: 360469 (The Pile)

Max Activating Token Index: 120

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.4846. Min Range: -1.4846

Max Act: 1.2007. Min Act: -0.0001

Data Index: 4569 (The Pile)

Max Activating Token Index: 981

Click toggle to see full text

Truncated

Full Text #19