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

Dataset: The Pile

Neuron 13 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7156. Min Range: -0.7156

Max Act: 0.7156. Min Act: -0.0000

Data Index: 316045 (The Pile)

Max Activating Token Index: 338

Text #1

Max Range: 0.7156. Min Range: -0.7156

Max Act: 0.6380. Min Act: -0.0000

Data Index: 835752 (The Pile)

Max Activating Token Index: 361

Text #2

Max Range: 0.7156. Min Range: -0.7156

Max Act: 0.7031. Min Act: -0.0000

Data Index: 796760 (The Pile)

Max Activating Token Index: 214

Text #3

Max Range: 0.7156. Min Range: -0.7156

Max Act: 0.6129. Min Act: -0.0000

Data Index: 402976 (The Pile)

Max Activating Token Index: 625

Text #4

Max Range: 0.7156. Min Range: -0.7156

Max Act: 0.6046. Min Act: -0.0000

Data Index: 129579 (The Pile)

Max Activating Token Index: 581

Text #5

Max Range: 0.7156. Min Range: -0.7156

Max Act: 0.5941. Min Act: -0.0000

Data Index: 943023 (The Pile)

Max Activating Token Index: 175

Text #6

Max Range: 0.7156. Min Range: -0.7156

Max Act: 0.5295. Min Act: -0.0000

Data Index: 77012 (The Pile)

Max Activating Token Index: 624

Text #7

Max Range: 0.7156. Min Range: -0.7156

Max Act: 0.4686. Min Act: -0.0000

Data Index: 1269971 (The Pile)

Max Activating Token Index: 282

Text #8

Max Range: 0.7156. Min Range: -0.7156

Max Act: 0.4966. Min Act: -0.0000

Data Index: 1869394 (The Pile)

Max Activating Token Index: 171

Text #9

Max Range: 0.7156. Min Range: -0.7156

Max Act: 0.5084. Min Act: -0.0000

Data Index: 208111 (The Pile)

Max Activating Token Index: 108

Text #10

Max Range: 0.7156. Min Range: -0.7156

Max Act: 0.4898. Min Act: -0.0000

Data Index: 1805765 (The Pile)

Max Activating Token Index: 471

Text #11

Max Range: 0.7156. Min Range: -0.7156

Max Act: 0.5774. Min Act: -0.0000

Data Index: 1431572 (The Pile)

Max Activating Token Index: 287

Text #12

Max Range: 0.7156. Min Range: -0.7156

Max Act: 0.4540. Min Act: -0.0000

Data Index: 1784465 (The Pile)

Max Activating Token Index: 74

Text #13

Max Range: 0.7156. Min Range: -0.7156

Max Act: 0.5198. Min Act: -0.0000

Data Index: 584416 (The Pile)

Max Activating Token Index: 321

Text #14

Max Range: 0.7156. Min Range: -0.7156

Max Act: 0.3999. Min Act: -0.0000

Data Index: 1923652 (The Pile)

Max Activating Token Index: 965

Text #15

Max Range: 0.7156. Min Range: -0.7156

Max Act: 0.5173. Min Act: -0.0000

Data Index: 174939 (The Pile)

Max Activating Token Index: 970

Text #16

Max Range: 0.7156. Min Range: -0.7156

Max Act: 0.4572. Min Act: -0.0000

Data Index: 288038 (The Pile)

Max Activating Token Index: 576

Text #17

Max Range: 0.7156. Min Range: -0.7156

Max Act: 0.4826. Min Act: -0.0000

Data Index: 1358399 (The Pile)

Max Activating Token Index: 157

Text #18

Max Range: 0.7156. Min Range: -0.7156

Max Act: 0.4439. Min Act: -0.0000

Data Index: 1309401 (The Pile)

Max Activating Token Index: 682

Text #19

Max Range: 0.7156. Min Range: -0.7156

Max Act: 0.4265. Min Act: -0.0000

Data Index: 171008 (The Pile)

Max Activating Token Index: 24