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

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

Neuron 2109 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1450. Min Act: -0.0000

Data Index: 841608 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1429. Min Act: -0.0000

Data Index: 222781 (C4 (Web Text))

Max Activating Token Index: 934

Text #2

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1364. Min Act: -0.0001

Data Index: 742382 (C4 (Web Text))

Max Activating Token Index: 336

Text #3

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1218. Min Act: -0.0000

Data Index: 651777 (C4 (Web Text))

Max Activating Token Index: 480

Text #4

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1207. Min Act: -0.0000

Data Index: 400058 (C4 (Web Text))

Max Activating Token Index: 574

Text #5

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1192. Min Act: -0.0000

Data Index: 843656 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1222. Min Act: -0.0000

Data Index: 1150376 (C4 (Web Text))

Max Activating Token Index: 964

Text #7

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1168. Min Act: -0.0000

Data Index: 534658 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1101. Min Act: 0.0001

Data Index: 1102695 (C4 (Web Text))

Max Activating Token Index: 214

Text #9

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1172. Min Act: -0.0000

Data Index: 1109333 (C4 (Web Text))

Max Activating Token Index: 504

Text #10

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1126. Min Act: -0.0000

Data Index: 914203 (C4 (Web Text))

Max Activating Token Index: 795

Text #11

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1128. Min Act: -0.0000

Data Index: 257351 (C4 (Web Text))

Max Activating Token Index: 297

Text #12

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1095. Min Act: -0.0000

Data Index: 751624 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1123. Min Act: -0.0001

Data Index: 66722 (C4 (Web Text))

Max Activating Token Index: 273

Text #14

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1155. Min Act: -0.0001

Data Index: 542576 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1098. Min Act: -0.0000

Data Index: 987986 (C4 (Web Text))

Max Activating Token Index: 915

Text #16

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1092. Min Act: -0.0001

Data Index: 1120304 (C4 (Web Text))

Max Activating Token Index: 207

Text #17

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1168. Min Act: -0.0000

Data Index: 513889 (C4 (Web Text))

Max Activating Token Index: 976

Text #18

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1036. Min Act: -0.0000

Data Index: 1319876 (C4 (Web Text))

Max Activating Token Index: 902

Text #19

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1022. Min Act: 0.0000

Data Index: 278108 (C4 (Web Text))

Max Activating Token Index: 65