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

Dataset: The Pile

Neuron 804 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.4269. Min Act: -0.0000

Data Index: 1694984 (The Pile)

Max Activating Token Index: 372

Text #1

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.4112. Min Act: -0.0000

Data Index: 885514 (The Pile)

Max Activating Token Index: 510

Text #2

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.3975. Min Act: -0.0000

Data Index: 344472 (The Pile)

Max Activating Token Index: 360

Text #3

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.3875. Min Act: -0.0000

Data Index: 551440 (The Pile)

Max Activating Token Index: 316

Text #4

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.3630. Min Act: -0.0000

Data Index: 807553 (The Pile)

Max Activating Token Index: 175

Text #5

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.3423. Min Act: -0.0000

Data Index: 513018 (The Pile)

Max Activating Token Index: 112

Text #6

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.3671. Min Act: -0.0000

Data Index: 225913 (The Pile)

Max Activating Token Index: 642

Text #7

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.3371. Min Act: -0.0000

Data Index: 799911 (The Pile)

Max Activating Token Index: 486

Text #8

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.3397. Min Act: -0.0000

Data Index: 1448790 (The Pile)

Max Activating Token Index: 707

Text #9

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.3248. Min Act: -0.0000

Data Index: 1144907 (The Pile)

Max Activating Token Index: 199

Text #10

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.3174. Min Act: -0.0000

Data Index: 579363 (The Pile)

Max Activating Token Index: 1007

Text #11

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.3359. Min Act: -0.0000

Data Index: 1603732 (The Pile)

Max Activating Token Index: 249

Text #12

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.3316. Min Act: -0.0000

Data Index: 1765296 (The Pile)

Max Activating Token Index: 635

Text #13

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.3227. Min Act: -0.0000

Data Index: 795307 (The Pile)

Max Activating Token Index: 265

Text #14

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.3181. Min Act: -0.0000

Data Index: 1417982 (The Pile)

Max Activating Token Index: 112

Text #15

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.3120. Min Act: -0.0000

Data Index: 1578499 (The Pile)

Max Activating Token Index: 850

Text #16

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.3240. Min Act: -0.0000

Data Index: 1623191 (The Pile)

Max Activating Token Index: 524

Text #17

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.3066. Min Act: -0.0000

Data Index: 1261273 (The Pile)

Max Activating Token Index: 466

Text #18

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.3155. Min Act: -0.0000

Data Index: 1497587 (The Pile)

Max Activating Token Index: 292

Text #19

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.3292. Min Act: -0.0000

Data Index: 607849 (The Pile)

Max Activating Token Index: 548