Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1152 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.1340. Min Act: -0.0001

Data Index: 934087 (C4 (Web Text))

Max Activating Token Index: 956

Text #1

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.1404. Min Act: -0.0001

Data Index: 444559 (C4 (Web Text))

Max Activating Token Index: 561

Text #2

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.1319. Min Act: -0.0001

Data Index: 1264538 (C4 (Web Text))

Max Activating Token Index: 1005

Text #3

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.1347. Min Act: -0.0001

Data Index: 205220 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.1305. Min Act: -0.0001

Data Index: 955373 (C4 (Web Text))

Max Activating Token Index: 506

Text #5

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.1255. Min Act: -0.0001

Data Index: 1166448 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.1256. Min Act: -0.0001

Data Index: 606278 (C4 (Web Text))

Max Activating Token Index: 311

Text #7

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.1260. Min Act: -0.0001

Data Index: 110014 (C4 (Web Text))

Max Activating Token Index: 92

Text #8

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.1175. Min Act: -0.0001

Data Index: 1211987 (C4 (Web Text))

Max Activating Token Index: 324

Text #9

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.1296. Min Act: -0.0001

Data Index: 105691 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.1258. Min Act: -0.0001

Data Index: 1226401 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.1222. Min Act: -0.0001

Data Index: 295414 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.1132. Min Act: -0.0001

Data Index: 764775 (C4 (Web Text))

Max Activating Token Index: 388

Text #13

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.1118. Min Act: -0.0001

Data Index: 273295 (C4 (Web Text))

Max Activating Token Index: 264

Text #14

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.1115. Min Act: -0.0001

Data Index: 3166 (C4 (Web Text))

Max Activating Token Index: 470

Text #15

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.1027. Min Act: -0.0001

Data Index: 101677 (C4 (Web Text))

Max Activating Token Index: 107

Text #16

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.1142. Min Act: -0.0001

Data Index: 1244837 (C4 (Web Text))

Max Activating Token Index: 393

Text #17

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.1173. Min Act: -0.0001

Data Index: 1156558 (C4 (Web Text))

Max Activating Token Index: 989

Text #18

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.1204. Min Act: -0.0001

Data Index: 680258 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.1082. Min Act: -0.0001

Data Index: 1229737 (C4 (Web Text))

Max Activating Token Index: 883