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

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

Neuron 3800 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1150. Min Act: -0.0000

Data Index: 1002627 (C4 (Web Text))

Max Activating Token Index: 933

Text #1

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1195. Min Act: -0.0000

Data Index: 363506 (C4 (Web Text))

Max Activating Token Index: 368

Text #2

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1295. Min Act: -0.0000

Data Index: 245335 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1138. Min Act: -0.0000

Data Index: 1329942 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1180. Min Act: -0.0000

Data Index: 683316 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1149. Min Act: -0.0000

Data Index: 803661 (C4 (Web Text))

Max Activating Token Index: 441

Text #6

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1217. Min Act: -0.0000

Data Index: 845073 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1007. Min Act: -0.0000

Data Index: 1046058 (C4 (Web Text))

Max Activating Token Index: 845

Text #8

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1166. Min Act: -0.0001

Data Index: 435488 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1123. Min Act: -0.0000

Data Index: 1121728 (C4 (Web Text))

Max Activating Token Index: 441

Text #10

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1166. Min Act: -0.0001

Data Index: 36677 (C4 (Web Text))

Max Activating Token Index: 973

Text #11

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1158. Min Act: -0.0001

Data Index: 59367 (C4 (Web Text))

Max Activating Token Index: 757

Text #12

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.0992. Min Act: -0.0001

Data Index: 605516 (C4 (Web Text))

Max Activating Token Index: 592

Text #13

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1137. Min Act: -0.0000

Data Index: 1356372 (C4 (Web Text))

Max Activating Token Index: 395

Text #14

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1151. Min Act: -0.0000

Data Index: 1263350 (C4 (Web Text))

Max Activating Token Index: 524

Text #15

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1187. Min Act: -0.0000

Data Index: 488502 (C4 (Web Text))

Max Activating Token Index: 533

Text #16

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1055. Min Act: -0.0000

Data Index: 1283454 (C4 (Web Text))

Max Activating Token Index: 463

Text #17

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1096. Min Act: -0.0001

Data Index: 538044 (C4 (Web Text))

Max Activating Token Index: 216

Text #18

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1047. Min Act: -0.0001

Data Index: 50592 (C4 (Web Text))

Max Activating Token Index: 149

Text #19

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1001. Min Act: -0.0001

Data Index: 858745 (C4 (Web Text))

Max Activating Token Index: 506