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

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

Neuron 1858 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: 0.0239. Min Range: -0.0239

Max Act: 0.0239. Min Act: -0.0004

Data Index: 283158 (C4 (Web Text))

Max Activating Token Index: 495

Text #1

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0189. Min Act: -0.0003

Data Index: 649907 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0160. Min Act: -0.0003

Data Index: 271092 (C4 (Web Text))

Max Activating Token Index: 541

Text #3

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0160. Min Act: -0.0003

Data Index: 831946 (C4 (Web Text))

Max Activating Token Index: 454

Text #4

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0155. Min Act: -0.0003

Data Index: 706474 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0160. Min Act: -0.0003

Data Index: 939294 (C4 (Web Text))

Max Activating Token Index: 868

Text #6

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0152. Min Act: -0.0003

Data Index: 1224650 (C4 (Web Text))

Max Activating Token Index: 447

Text #7

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0149. Min Act: -0.0004

Data Index: 1042477 (C4 (Web Text))

Max Activating Token Index: 352

Text #8

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0149. Min Act: -0.0003

Data Index: 527168 (C4 (Web Text))

Max Activating Token Index: 614

Text #9

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0154. Min Act: -0.0003

Data Index: 410520 (C4 (Web Text))

Max Activating Token Index: 370

Text #10

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0153. Min Act: -0.0003

Data Index: 1313030 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0157. Min Act: -0.0003

Data Index: 726224 (C4 (Web Text))

Max Activating Token Index: 427

Text #12

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0151. Min Act: -0.0003

Data Index: 674993 (C4 (Web Text))

Max Activating Token Index: 773

Text #13

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0151. Min Act: -0.0003

Data Index: 1086954 (C4 (Web Text))

Max Activating Token Index: 479

Text #14

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0150. Min Act: -0.0003

Data Index: 1248038 (C4 (Web Text))

Max Activating Token Index: 148

Text #15

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0141. Min Act: -0.0003

Data Index: 1019029 (C4 (Web Text))

Max Activating Token Index: 368

Text #16

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0150. Min Act: -0.0003

Data Index: 718128 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0152. Min Act: -0.0003

Data Index: 1189002 (C4 (Web Text))

Max Activating Token Index: 871

Text #18

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0143. Min Act: -0.0003

Data Index: 1103694 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0151. Min Act: -0.0003

Data Index: 395849 (C4 (Web Text))

Max Activating Token Index: 451