Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 102 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0193. Min Act: -0.0005

Data Index: 108596 (C4 (Web Text))

Max Activating Token Index: 168

Text #1

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0197. Min Act: -0.0005

Data Index: 736950 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0192. Min Act: -0.0005

Data Index: 825860 (C4 (Web Text))

Max Activating Token Index: 569

Text #3

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0171. Min Act: -0.0005

Data Index: 1119851 (C4 (Web Text))

Max Activating Token Index: 819

Text #4

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0172. Min Act: -0.0005

Data Index: 809403 (C4 (Web Text))

Max Activating Token Index: 647

Text #5

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0172. Min Act: -0.0005

Data Index: 575719 (C4 (Web Text))

Max Activating Token Index: 869

Text #6

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0170. Min Act: -0.0006

Data Index: 454562 (C4 (Web Text))

Max Activating Token Index: 719

Text #7

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0165. Min Act: -0.0005

Data Index: 1564884 (Python Code)

Max Activating Token Index: 715

Text #8

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0166. Min Act: -0.0005

Data Index: 1192565 (C4 (Web Text))

Max Activating Token Index: 850

Text #9

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0163. Min Act: -0.0006

Data Index: 1270461 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0163. Min Act: -0.0005

Data Index: 1149172 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0155. Min Act: -0.0006

Data Index: 651782 (C4 (Web Text))

Max Activating Token Index: 386

Text #12

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0159. Min Act: -0.0004

Data Index: 1004270 (C4 (Web Text))

Max Activating Token Index: 647

Text #13

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0157. Min Act: -0.0005

Data Index: 908341 (C4 (Web Text))

Max Activating Token Index: 63

Text #14

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0157. Min Act: -0.0005

Data Index: 508387 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0157. Min Act: -0.0005

Data Index: 877215 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0156. Min Act: -0.0005

Data Index: 427904 (C4 (Web Text))

Max Activating Token Index: 186

Text #17

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0152. Min Act: -0.0005

Data Index: 1551150 (Python Code)

Max Activating Token Index: 17

Text #18

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0151. Min Act: -0.0005

Data Index: 539574 (C4 (Web Text))

Max Activating Token Index: 776

Text #19

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0150. Min Act: -0.0006

Data Index: 1203179 (C4 (Web Text))

Max Activating Token Index: 776