< Prev | Home | Model | Random | Next >

Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: The Pile

Neuron 2046 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l-pile')



Text #0

Max Range: 0.3388. Min Range: -0.3388

Max Act: 0.3388. Min Act: -0.0004

Data Index: 1050705 (The Pile)

Max Activating Token Index: 293

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.3388. Min Range: -0.3388

Max Act: 0.3143. Min Act: -0.0004

Data Index: 1929865 (The Pile)

Max Activating Token Index: 182

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.3388. Min Range: -0.3388

Max Act: 0.2933. Min Act: -0.0004

Data Index: 400494 (The Pile)

Max Activating Token Index: 811

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.3388. Min Range: -0.3388

Max Act: 0.2777. Min Act: -0.0004

Data Index: 1246140 (The Pile)

Max Activating Token Index: 31

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.3388. Min Range: -0.3388

Max Act: 0.2607. Min Act: -0.0004

Data Index: 661996 (The Pile)

Max Activating Token Index: 316

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.3388. Min Range: -0.3388

Max Act: 0.2642. Min Act: -0.0004

Data Index: 243003 (The Pile)

Max Activating Token Index: 921

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.3388. Min Range: -0.3388

Max Act: 0.2531. Min Act: -0.0004

Data Index: 139536 (The Pile)

Max Activating Token Index: 820

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.3388. Min Range: -0.3388

Max Act: 0.2591. Min Act: -0.0004

Data Index: 245438 (The Pile)

Max Activating Token Index: 431

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.3388. Min Range: -0.3388

Max Act: 0.2468. Min Act: -0.0004

Data Index: 797132 (The Pile)

Max Activating Token Index: 102

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.3388. Min Range: -0.3388

Max Act: 0.2442. Min Act: -0.0004

Data Index: 1400946 (The Pile)

Max Activating Token Index: 168

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.3388. Min Range: -0.3388

Max Act: 0.2356. Min Act: -0.0004

Data Index: 140857 (The Pile)

Max Activating Token Index: 796

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.3388. Min Range: -0.3388

Max Act: 0.2192. Min Act: -0.0004

Data Index: 1539722 (The Pile)

Max Activating Token Index: 524

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.3388. Min Range: -0.3388

Max Act: 0.2283. Min Act: -0.0004

Data Index: 1192461 (The Pile)

Max Activating Token Index: 574

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.3388. Min Range: -0.3388

Max Act: 0.2303. Min Act: -0.0004

Data Index: 1647241 (The Pile)

Max Activating Token Index: 232

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.3388. Min Range: -0.3388

Max Act: 0.2270. Min Act: -0.0004

Data Index: 1776056 (The Pile)

Max Activating Token Index: 259

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.3388. Min Range: -0.3388

Max Act: 0.2378. Min Act: -0.0004

Data Index: 740756 (The Pile)

Max Activating Token Index: 675

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.3388. Min Range: -0.3388

Max Act: 0.2431. Min Act: -0.0004

Data Index: 333471 (The Pile)

Max Activating Token Index: 28

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.3388. Min Range: -0.3388

Max Act: 0.2417. Min Act: -0.0004

Data Index: 590942 (The Pile)

Max Activating Token Index: 903

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.3388. Min Range: -0.3388

Max Act: 0.2314. Min Act: -0.0004

Data Index: 1384168 (The Pile)

Max Activating Token Index: 56

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.3388. Min Range: -0.3388

Max Act: 0.2639. Min Act: -0.0004

Data Index: 161402 (The Pile)

Max Activating Token Index: 344

Click toggle to see full text

Truncated

Full Text #19