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

Dataset: The Pile

Neuron 3053 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.3151. Min Act: -0.0000

Data Index: 1824733 (The Pile)

Max Activating Token Index: 741

Text #1

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.3088. Min Act: -0.0000

Data Index: 1643140 (The Pile)

Max Activating Token Index: 617

Text #2

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.2601. Min Act: -0.0000

Data Index: 1764545 (The Pile)

Max Activating Token Index: 887

Text #3

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.2379. Min Act: -0.0000

Data Index: 922525 (The Pile)

Max Activating Token Index: 296

Text #4

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.2216. Min Act: -0.0000

Data Index: 1025700 (The Pile)

Max Activating Token Index: 324

Text #5

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.2149. Min Act: -0.0000

Data Index: 1821506 (The Pile)

Max Activating Token Index: 912

Text #6

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.2176. Min Act: -0.0000

Data Index: 632494 (The Pile)

Max Activating Token Index: 109

Text #7

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.2191. Min Act: -0.0000

Data Index: 843998 (The Pile)

Max Activating Token Index: 497

Text #8

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.2218. Min Act: -0.0000

Data Index: 1333730 (The Pile)

Max Activating Token Index: 186

Text #9

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.2284. Min Act: -0.0000

Data Index: 1420574 (The Pile)

Max Activating Token Index: 148

Text #10

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.2136. Min Act: -0.0000

Data Index: 1445956 (The Pile)

Max Activating Token Index: 359

Text #11

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.2101. Min Act: -0.0000

Data Index: 1434494 (The Pile)

Max Activating Token Index: 982

Text #12

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.2059. Min Act: -0.0000

Data Index: 756736 (The Pile)

Max Activating Token Index: 583

Text #13

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.1732. Min Act: -0.0000

Data Index: 1812585 (The Pile)

Max Activating Token Index: 906

Text #14

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.2164. Min Act: -0.0000

Data Index: 52942 (The Pile)

Max Activating Token Index: 28

Text #15

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.2157. Min Act: -0.0000

Data Index: 879251 (The Pile)

Max Activating Token Index: 168

Text #16

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.2000. Min Act: -0.0000

Data Index: 853833 (The Pile)

Max Activating Token Index: 1009

Text #17

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.2054. Min Act: -0.0000

Data Index: 1557044 (The Pile)

Max Activating Token Index: 784

Text #18

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.1749. Min Act: -0.0000

Data Index: 1485005 (The Pile)

Max Activating Token Index: 829

Text #19

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.1985. Min Act: -0.0000

Data Index: 1656052 (The Pile)

Max Activating Token Index: 619