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

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

Neuron 5079 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1310. Min Act: -0.0001

Data Index: 926586 (C4 (Web Text))

Max Activating Token Index: 281

Text #1

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1330. Min Act: -0.0001

Data Index: 495012 (C4 (Web Text))

Max Activating Token Index: 567

Text #2

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1303. Min Act: -0.0001

Data Index: 1120093 (C4 (Web Text))

Max Activating Token Index: 1019

Text #3

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1277. Min Act: -0.0001

Data Index: 360640 (C4 (Web Text))

Max Activating Token Index: 991

Text #4

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1383. Min Act: -0.0001

Data Index: 263715 (C4 (Web Text))

Max Activating Token Index: 407

Text #5

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1221. Min Act: -0.0001

Data Index: 440162 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1165. Min Act: -0.0001

Data Index: 155984 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1337. Min Act: -0.0001

Data Index: 1011555 (C4 (Web Text))

Max Activating Token Index: 870

Text #8

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1250. Min Act: -0.0001

Data Index: 42142 (C4 (Web Text))

Max Activating Token Index: 1020

Text #9

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1129. Min Act: -0.0001

Data Index: 1341283 (C4 (Web Text))

Max Activating Token Index: 963

Text #10

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1136. Min Act: -0.0001

Data Index: 1358652 (C4 (Web Text))

Max Activating Token Index: 815

Text #11

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1168. Min Act: -0.0001

Data Index: 816709 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1178. Min Act: -0.0001

Data Index: 188474 (C4 (Web Text))

Max Activating Token Index: 381

Text #13

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1092. Min Act: -0.0001

Data Index: 1003062 (C4 (Web Text))

Max Activating Token Index: 492

Text #14

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1068. Min Act: -0.0001

Data Index: 84772 (C4 (Web Text))

Max Activating Token Index: 410

Text #15

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1068. Min Act: -0.0001

Data Index: 831450 (C4 (Web Text))

Max Activating Token Index: 850

Text #16

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1096. Min Act: -0.0001

Data Index: 406434 (C4 (Web Text))

Max Activating Token Index: 700

Text #17

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1124. Min Act: -0.0001

Data Index: 785372 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1033. Min Act: -0.0001

Data Index: 663208 (C4 (Web Text))

Max Activating Token Index: 873

Text #19

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1085. Min Act: -0.0001

Data Index: 1230422 (C4 (Web Text))

Max Activating Token Index: 195