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

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

Neuron 3876 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0192. Min Act: -0.0003

Data Index: 170125 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0205. Min Act: -0.0003

Data Index: 805783 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0192. Min Act: -0.0003

Data Index: 550233 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0180. Min Act: -0.0003

Data Index: 885344 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0166. Min Act: -0.0003

Data Index: 205313 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0189. Min Act: -0.0003

Data Index: 631390 (C4 (Web Text))

Max Activating Token Index: 787

Text #6

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0145. Min Act: -0.0003

Data Index: 319164 (C4 (Web Text))

Max Activating Token Index: 635

Text #7

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0180. Min Act: -0.0003

Data Index: 122051 (C4 (Web Text))

Max Activating Token Index: 471

Text #8

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0148. Min Act: -0.0003

Data Index: 720021 (C4 (Web Text))

Max Activating Token Index: 246

Text #9

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0157. Min Act: -0.0003

Data Index: 1536052 (Python Code)

Max Activating Token Index: 608

Text #10

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0163. Min Act: -0.0003

Data Index: 669030 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0161. Min Act: -0.0003

Data Index: 1174384 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0158. Min Act: -0.0003

Data Index: 174706 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0156. Min Act: -0.0003

Data Index: 157096 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0137. Min Act: -0.0003

Data Index: 288741 (C4 (Web Text))

Max Activating Token Index: 464

Text #15

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0148. Min Act: -0.0003

Data Index: 472461 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0147. Min Act: -0.0003

Data Index: 987434 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0124. Min Act: -0.0003

Data Index: 170952 (C4 (Web Text))

Max Activating Token Index: 194

Text #18

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0143. Min Act: -0.0003

Data Index: 736902 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0145. Min Act: -0.0002

Data Index: 1495870 (Python Code)

Max Activating Token Index: 791