Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2256 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 14.6358. Min Range: -14.6358

Max Act: 14.6358. Min Act: -0.0000

Data Index: 546260 (The Pile)

Max Activating Token Index: 202

Text #1

Max Range: 14.6358. Min Range: -14.6358

Max Act: 14.3538. Min Act: -0.0000

Data Index: 79873 (The Pile)

Max Activating Token Index: 117

Text #2

Max Range: 14.6358. Min Range: -14.6358

Max Act: 14.2150. Min Act: -0.0000

Data Index: 962359 (The Pile)

Max Activating Token Index: 236

Text #3

Max Range: 14.6358. Min Range: -14.6358

Max Act: 14.1950. Min Act: -0.0000

Data Index: 1262425 (The Pile)

Max Activating Token Index: 410

Text #4

Max Range: 14.6358. Min Range: -14.6358

Max Act: 13.8384. Min Act: -0.0000

Data Index: 1602461 (The Pile)

Max Activating Token Index: 56

Text #5

Max Range: 14.6358. Min Range: -14.6358

Max Act: 13.9223. Min Act: -0.0000

Data Index: 1210050 (The Pile)

Max Activating Token Index: 120

Text #6

Max Range: 14.6358. Min Range: -14.6358

Max Act: 13.8523. Min Act: -0.0000

Data Index: 413451 (The Pile)

Max Activating Token Index: 134

Text #7

Max Range: 14.6358. Min Range: -14.6358

Max Act: 13.7502. Min Act: -0.0000

Data Index: 855912 (The Pile)

Max Activating Token Index: 395

Text #8

Max Range: 14.6358. Min Range: -14.6358

Max Act: 13.8207. Min Act: -0.0000

Data Index: 625537 (The Pile)

Max Activating Token Index: 28

Text #9

Max Range: 14.6358. Min Range: -14.6358

Max Act: 13.8338. Min Act: -0.0000

Data Index: 1688301 (The Pile)

Max Activating Token Index: 336

Text #10

Max Range: 14.6358. Min Range: -14.6358

Max Act: 13.7511. Min Act: -0.0000

Data Index: 385107 (The Pile)

Max Activating Token Index: 158

Text #11

Max Range: 14.6358. Min Range: -14.6358

Max Act: 13.6725. Min Act: -0.0000

Data Index: 1330465 (The Pile)

Max Activating Token Index: 331

Text #12

Max Range: 14.6358. Min Range: -14.6358

Max Act: 13.9778. Min Act: -0.0000

Data Index: 50583 (The Pile)

Max Activating Token Index: 27

Text #13

Max Range: 14.6358. Min Range: -14.6358

Max Act: 13.6959. Min Act: -0.0000

Data Index: 616962 (The Pile)

Max Activating Token Index: 41

Text #14

Max Range: 14.6358. Min Range: -14.6358

Max Act: 13.5245. Min Act: -0.0000

Data Index: 1160582 (The Pile)

Max Activating Token Index: 479

Text #15

Max Range: 14.6358. Min Range: -14.6358

Max Act: 13.5108. Min Act: -0.0000

Data Index: 1754035 (The Pile)

Max Activating Token Index: 360

Text #16

Max Range: 14.6358. Min Range: -14.6358

Max Act: 13.4496. Min Act: -0.0000

Data Index: 1454370 (The Pile)

Max Activating Token Index: 329

Text #17

Max Range: 14.6358. Min Range: -14.6358

Max Act: 13.5243. Min Act: -0.0000

Data Index: 1398982 (The Pile)

Max Activating Token Index: 36

Text #18

Max Range: 14.6358. Min Range: -14.6358

Max Act: 13.5247. Min Act: -0.0000

Data Index: 1699884 (The Pile)

Max Activating Token Index: 12

Text #19

Max Range: 14.6358. Min Range: -14.6358

Max Act: 13.4369. Min Act: -0.0000

Data Index: 165808 (The Pile)

Max Activating Token Index: 72