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

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

Neuron 1167 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0279. Min Act: -0.0002

Data Index: 1237002 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0160. Min Act: -0.0002

Data Index: 290526 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0157. Min Act: -0.0002

Data Index: 832833 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0151. Min Act: -0.0002

Data Index: 1327998 (C4 (Web Text))

Max Activating Token Index: 868

Text #4

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0151. Min Act: -0.0002

Data Index: 484235 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0148. Min Act: -0.0002

Data Index: 174304 (C4 (Web Text))

Max Activating Token Index: 927

Text #6

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0145. Min Act: -0.0002

Data Index: 627822 (C4 (Web Text))

Max Activating Token Index: 111

Text #7

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0143. Min Act: -0.0002

Data Index: 1160346 (C4 (Web Text))

Max Activating Token Index: 676

Text #8

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0138. Min Act: -0.0002

Data Index: 1330405 (C4 (Web Text))

Max Activating Token Index: 952

Text #9

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0138. Min Act: -0.0002

Data Index: 1139667 (C4 (Web Text))

Max Activating Token Index: 915

Text #10

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0138. Min Act: -0.0002

Data Index: 461426 (C4 (Web Text))

Max Activating Token Index: 206

Text #11

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0137. Min Act: -0.0002

Data Index: 513438 (C4 (Web Text))

Max Activating Token Index: 934

Text #12

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0137. Min Act: -0.0002

Data Index: 1052623 (C4 (Web Text))

Max Activating Token Index: 363

Text #13

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0136. Min Act: -0.0002

Data Index: 234756 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0134. Min Act: -0.0002

Data Index: 1060571 (C4 (Web Text))

Max Activating Token Index: 171

Text #15

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0135. Min Act: -0.0002

Data Index: 155391 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0134. Min Act: -0.0002

Data Index: 975251 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0134. Min Act: -0.0002

Data Index: 222331 (C4 (Web Text))

Max Activating Token Index: 644

Text #18

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0133. Min Act: -0.0002

Data Index: 518485 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0132. Min Act: -0.0002

Data Index: 982307 (C4 (Web Text))

Max Activating Token Index: 60