Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1124 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1359. Min Act: -0.0005

Data Index: 1131841 (C4 (Web Text))

Max Activating Token Index: 242

Text #1

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1224. Min Act: -0.0005

Data Index: 762138 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1100. Min Act: -0.0005

Data Index: 1038180 (C4 (Web Text))

Max Activating Token Index: 954

Text #3

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1185. Min Act: -0.0005

Data Index: 920595 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1329. Min Act: -0.0005

Data Index: 496655 (C4 (Web Text))

Max Activating Token Index: 341

Text #5

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1122. Min Act: -0.0005

Data Index: 188098 (C4 (Web Text))

Max Activating Token Index: 466

Text #6

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1099. Min Act: -0.0005

Data Index: 521624 (C4 (Web Text))

Max Activating Token Index: 390

Text #7

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1162. Min Act: -0.0005

Data Index: 216652 (C4 (Web Text))

Max Activating Token Index: 972

Text #8

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1117. Min Act: -0.0005

Data Index: 849936 (C4 (Web Text))

Max Activating Token Index: 900

Text #9

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1132. Min Act: -0.0005

Data Index: 57948 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1272. Min Act: -0.0005

Data Index: 949295 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1175. Min Act: -0.0005

Data Index: 1365927 (Python Code)

Max Activating Token Index: 59

Text #12

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1169. Min Act: -0.0005

Data Index: 1192325 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1116. Min Act: -0.0005

Data Index: 170423 (C4 (Web Text))

Max Activating Token Index: 852

Text #14

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1126. Min Act: -0.0005

Data Index: 447597 (C4 (Web Text))

Max Activating Token Index: 1001

Text #15

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1152. Min Act: -0.0005

Data Index: 172906 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1124. Min Act: -0.0005

Data Index: 1107389 (C4 (Web Text))

Max Activating Token Index: 548

Text #17

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1085. Min Act: -0.0005

Data Index: 838125 (C4 (Web Text))

Max Activating Token Index: 878

Text #18

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1056. Min Act: -0.0005

Data Index: 351713 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1071. Min Act: -0.0005

Data Index: 1359396 (C4 (Web Text))

Max Activating Token Index: 272