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

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

Neuron 425 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1263. Min Act: -0.0002

Data Index: 195322 (C4 (Web Text))

Max Activating Token Index: 333

Text #1

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1150. Min Act: -0.0002

Data Index: 1113558 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1023. Min Act: -0.0002

Data Index: 1353589 (C4 (Web Text))

Max Activating Token Index: 239

Text #3

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1173. Min Act: -0.0002

Data Index: 85315 (C4 (Web Text))

Max Activating Token Index: 145

Text #4

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1362. Min Act: -0.0002

Data Index: 1136682 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1180. Min Act: -0.0002

Data Index: 1132561 (C4 (Web Text))

Max Activating Token Index: 370

Text #6

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1168. Min Act: -0.0002

Data Index: 1147851 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1337. Min Act: -0.0002

Data Index: 542830 (C4 (Web Text))

Max Activating Token Index: 645

Text #8

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1160. Min Act: -0.0002

Data Index: 26323 (C4 (Web Text))

Max Activating Token Index: 326

Text #9

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1084. Min Act: -0.0002

Data Index: 1134476 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1097. Min Act: -0.0002

Data Index: 1156317 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1112. Min Act: -0.0002

Data Index: 361304 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1213. Min Act: -0.0002

Data Index: 280323 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.0986. Min Act: -0.0002

Data Index: 733632 (C4 (Web Text))

Max Activating Token Index: 901

Text #14

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1242. Min Act: -0.0002

Data Index: 1143615 (C4 (Web Text))

Max Activating Token Index: 224

Text #15

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.0999. Min Act: -0.0002

Data Index: 1332189 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1230. Min Act: -0.0002

Data Index: 1207226 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1081. Min Act: -0.0002

Data Index: 185447 (C4 (Web Text))

Max Activating Token Index: 106

Text #18

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1076. Min Act: -0.0002

Data Index: 316940 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1151. Min Act: -0.0002

Data Index: 996460 (C4 (Web Text))

Max Activating Token Index: 975