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

Dataset: The Pile

Neuron 1055 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: 0.0279. Min Range: -0.0279

Max Act: 0.0279. Min Act: -0.0000

Data Index: 1833867 (The Pile)

Max Activating Token Index: 782

Text #1

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0190. Min Act: -0.0000

Data Index: 312910 (The Pile)

Max Activating Token Index: 996

Text #2

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0192. Min Act: -0.0000

Data Index: 377470 (The Pile)

Max Activating Token Index: 385

Text #3

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0178. Min Act: -0.0000

Data Index: 1623519 (The Pile)

Max Activating Token Index: 251

Text #4

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0166. Min Act: -0.0000

Data Index: 1481721 (The Pile)

Max Activating Token Index: 1022

Text #5

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0174. Min Act: -0.0000

Data Index: 536238 (The Pile)

Max Activating Token Index: 273

Text #6

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0173. Min Act: -0.0000

Data Index: 873883 (The Pile)

Max Activating Token Index: 696

Text #7

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0163. Min Act: -0.0000

Data Index: 1165328 (The Pile)

Max Activating Token Index: 415

Text #8

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0168. Min Act: -0.0000

Data Index: 531971 (The Pile)

Max Activating Token Index: 550

Text #9

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0167. Min Act: -0.0000

Data Index: 1490647 (The Pile)

Max Activating Token Index: 675

Text #10

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0161. Min Act: -0.0000

Data Index: 910751 (The Pile)

Max Activating Token Index: 829

Text #11

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0166. Min Act: -0.0000

Data Index: 859050 (The Pile)

Max Activating Token Index: 956

Text #12

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0163. Min Act: -0.0000

Data Index: 1994828 (The Pile)

Max Activating Token Index: 769

Text #13

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0151. Min Act: -0.0000

Data Index: 1303924 (The Pile)

Max Activating Token Index: 665

Text #14

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0150. Min Act: -0.0000

Data Index: 682782 (The Pile)

Max Activating Token Index: 282

Text #15

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0158. Min Act: -0.0000

Data Index: 1952443 (The Pile)

Max Activating Token Index: 1007

Text #16

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0141. Min Act: -0.0000

Data Index: 277394 (The Pile)

Max Activating Token Index: 906

Text #17

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0135. Min Act: -0.0000

Data Index: 839003 (The Pile)

Max Activating Token Index: 904

Text #18

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0137. Min Act: -0.0000

Data Index: 1129126 (The Pile)

Max Activating Token Index: 572

Text #19

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0141. Min Act: -0.0000

Data Index: 453204 (The Pile)

Max Activating Token Index: 191