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

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

Neuron 1424 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: 0.1452. Min Range: -0.1452

Max Act: 0.1452. Min Act: -0.0001

Data Index: 700242 (C4 (Web Text))

Max Activating Token Index: 354

Text #1

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1409. Min Act: -0.0001

Data Index: 1335450 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1283. Min Act: -0.0001

Data Index: 76470 (C4 (Web Text))

Max Activating Token Index: 994

Text #3

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1305. Min Act: -0.0001

Data Index: 1359701 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1309. Min Act: -0.0001

Data Index: 1188952 (C4 (Web Text))

Max Activating Token Index: 705

Text #5

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1311. Min Act: -0.0001

Data Index: 533873 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1158. Min Act: -0.0001

Data Index: 534161 (C4 (Web Text))

Max Activating Token Index: 952

Text #7

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1207. Min Act: -0.0001

Data Index: 316708 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1226. Min Act: -0.0001

Data Index: 464677 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1189. Min Act: -0.0001

Data Index: 286354 (C4 (Web Text))

Max Activating Token Index: 845

Text #10

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1166. Min Act: -0.0001

Data Index: 991472 (C4 (Web Text))

Max Activating Token Index: 377

Text #11

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1153. Min Act: -0.0001

Data Index: 818019 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1150. Min Act: -0.0000

Data Index: 812647 (C4 (Web Text))

Max Activating Token Index: 166

Text #13

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1107. Min Act: -0.0001

Data Index: 652848 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1083. Min Act: -0.0001

Data Index: 845239 (C4 (Web Text))

Max Activating Token Index: 1003

Text #15

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1045. Min Act: -0.0001

Data Index: 1280251 (C4 (Web Text))

Max Activating Token Index: 831

Text #16

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1164. Min Act: -0.0001

Data Index: 1265354 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1133. Min Act: -0.0001

Data Index: 1210660 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1127. Min Act: -0.0001

Data Index: 916714 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1192. Min Act: -0.0000

Data Index: 27491 (C4 (Web Text))

Max Activating Token Index: 518