Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3361 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0262. Min Act: -0.0003

Data Index: 165959 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0177. Min Act: -0.0003

Data Index: 635135 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0174. Min Act: -0.0003

Data Index: 343173 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0179. Min Act: -0.0003

Data Index: 442063 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0179. Min Act: -0.0003

Data Index: 1167337 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0183. Min Act: -0.0003

Data Index: 72627 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0158. Min Act: -0.0003

Data Index: 251775 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0158. Min Act: -0.0003

Data Index: 1227906 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0134. Min Act: -0.0003

Data Index: 732207 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0150. Min Act: -0.0003

Data Index: 1245709 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0153. Min Act: -0.0003

Data Index: 790233 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0153. Min Act: -0.0003

Data Index: 541030 (C4 (Web Text))

Max Activating Token Index: 929

Text #12

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0155. Min Act: -0.0003

Data Index: 979128 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0152. Min Act: -0.0003

Data Index: 267976 (C4 (Web Text))

Max Activating Token Index: 461

Text #14

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0149. Min Act: -0.0003

Data Index: 438432 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0148. Min Act: -0.0003

Data Index: 831269 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0144. Min Act: -0.0003

Data Index: 698042 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0158. Min Act: -0.0003

Data Index: 1144656 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0140. Min Act: -0.0003

Data Index: 1135994 (C4 (Web Text))

Max Activating Token Index: 827

Text #19

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0146. Min Act: -0.0003

Data Index: 636136 (C4 (Web Text))

Max Activating Token Index: 1023