Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2908 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0193. Min Act: -0.0002

Data Index: 287142 (C4 (Web Text))

Max Activating Token Index: 338

Text #1

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0207. Min Act: -0.0002

Data Index: 443657 (C4 (Web Text))

Max Activating Token Index: 295

Text #2

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0182. Min Act: -0.0002

Data Index: 662816 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0216. Min Act: -0.0002

Data Index: 1220100 (C4 (Web Text))

Max Activating Token Index: 366

Text #4

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0176. Min Act: -0.0002

Data Index: 225893 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0150. Min Act: -0.0002

Data Index: 1327522 (C4 (Web Text))

Max Activating Token Index: 437

Text #6

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0178. Min Act: -0.0002

Data Index: 57230 (C4 (Web Text))

Max Activating Token Index: 771

Text #7

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0162. Min Act: -0.0002

Data Index: 829111 (C4 (Web Text))

Max Activating Token Index: 416

Text #8

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0161. Min Act: -0.0002

Data Index: 499099 (C4 (Web Text))

Max Activating Token Index: 571

Text #9

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0172. Min Act: -0.0002

Data Index: 810111 (C4 (Web Text))

Max Activating Token Index: 881

Text #10

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0155. Min Act: -0.0002

Data Index: 812088 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0160. Min Act: -0.0002

Data Index: 526998 (C4 (Web Text))

Max Activating Token Index: 484

Text #12

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0141. Min Act: -0.0002

Data Index: 1229881 (C4 (Web Text))

Max Activating Token Index: 603

Text #13

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0139. Min Act: -0.0002

Data Index: 938445 (C4 (Web Text))

Max Activating Token Index: 395

Text #14

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0133. Min Act: -0.0002

Data Index: 577014 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0124. Min Act: -0.0002

Data Index: 1032122 (C4 (Web Text))

Max Activating Token Index: 231

Text #16

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0155. Min Act: -0.0002

Data Index: 1058950 (C4 (Web Text))

Max Activating Token Index: 453

Text #17

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0143. Min Act: -0.0002

Data Index: 647449 (C4 (Web Text))

Max Activating Token Index: 509

Text #18

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0136. Min Act: -0.0002

Data Index: 605224 (C4 (Web Text))

Max Activating Token Index: 1021

Text #19

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0142. Min Act: -0.0002

Data Index: 1232644 (C4 (Web Text))

Max Activating Token Index: 203