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

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

Neuron 2000 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0206. Min Act: -0.0006

Data Index: 1115382 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0184. Min Act: -0.0006

Data Index: 252736 (C4 (Web Text))

Max Activating Token Index: 515

Text #2

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0165. Min Act: -0.0006

Data Index: 233780 (C4 (Web Text))

Max Activating Token Index: 435

Text #3

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0175. Min Act: -0.0006

Data Index: 234205 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0175. Min Act: -0.0006

Data Index: 781273 (C4 (Web Text))

Max Activating Token Index: 303

Text #5

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0163. Min Act: -0.0006

Data Index: 818060 (C4 (Web Text))

Max Activating Token Index: 197

Text #6

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0160. Min Act: -0.0006

Data Index: 579192 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0157. Min Act: -0.0006

Data Index: 905213 (C4 (Web Text))

Max Activating Token Index: 565

Text #8

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0152. Min Act: -0.0006

Data Index: 51062 (C4 (Web Text))

Max Activating Token Index: 1012

Text #9

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0155. Min Act: -0.0006

Data Index: 468867 (C4 (Web Text))

Max Activating Token Index: 516

Text #10

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0152. Min Act: -0.0006

Data Index: 925300 (C4 (Web Text))

Max Activating Token Index: 975

Text #11

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0151. Min Act: -0.0006

Data Index: 619768 (C4 (Web Text))

Max Activating Token Index: 642

Text #12

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0146. Min Act: -0.0006

Data Index: 963825 (C4 (Web Text))

Max Activating Token Index: 205

Text #13

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0140. Min Act: -0.0006

Data Index: 29273 (C4 (Web Text))

Max Activating Token Index: 639

Text #14

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0145. Min Act: -0.0006

Data Index: 529048 (C4 (Web Text))

Max Activating Token Index: 944

Text #15

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0147. Min Act: -0.0006

Data Index: 1209235 (C4 (Web Text))

Max Activating Token Index: 539

Text #16

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0143. Min Act: -0.0006

Data Index: 314230 (C4 (Web Text))

Max Activating Token Index: 68

Text #17

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0145. Min Act: -0.0006

Data Index: 548016 (C4 (Web Text))

Max Activating Token Index: 499

Text #18

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0146. Min Act: -0.0006

Data Index: 177733 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0149. Min Act: -0.0006

Data Index: 505700 (C4 (Web Text))

Max Activating Token Index: 912