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

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

Neuron 2179 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1407. Min Act: -0.0001

Data Index: 1134326 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1300. Min Act: -0.0001

Data Index: 388288 (C4 (Web Text))

Max Activating Token Index: 134

Text #2

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1292. Min Act: -0.0001

Data Index: 127920 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1206. Min Act: -0.0001

Data Index: 693383 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1229. Min Act: -0.0001

Data Index: 1344179 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1156. Min Act: -0.0001

Data Index: 297755 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1217. Min Act: -0.0001

Data Index: 1023939 (C4 (Web Text))

Max Activating Token Index: 617

Text #7

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1170. Min Act: -0.0000

Data Index: 885565 (C4 (Web Text))

Max Activating Token Index: 227

Text #8

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1158. Min Act: -0.0001

Data Index: 652436 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1109. Min Act: -0.0001

Data Index: 872225 (C4 (Web Text))

Max Activating Token Index: 846

Text #10

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1277. Min Act: -0.0001

Data Index: 1038349 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1093. Min Act: -0.0001

Data Index: 186651 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1303. Min Act: -0.0001

Data Index: 1266806 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1116. Min Act: -0.0001

Data Index: 1310195 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1106. Min Act: -0.0001

Data Index: 468404 (C4 (Web Text))

Max Activating Token Index: 536

Text #15

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1099. Min Act: -0.0001

Data Index: 678506 (C4 (Web Text))

Max Activating Token Index: 222

Text #16

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1098. Min Act: -0.0001

Data Index: 788349 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1142. Min Act: -0.0001

Data Index: 1092912 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1091. Min Act: -0.0000

Data Index: 1113300 (C4 (Web Text))

Max Activating Token Index: 926

Text #19

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1016. Min Act: -0.0001

Data Index: 45534 (C4 (Web Text))

Max Activating Token Index: 277