Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3158 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1406. Min Act: -0.0001

Data Index: 534073 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1288. Min Act: -0.0001

Data Index: 924002 (C4 (Web Text))

Max Activating Token Index: 474

Text #2

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1305. Min Act: -0.0000

Data Index: 336256 (C4 (Web Text))

Max Activating Token Index: 573

Text #3

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1328. Min Act: -0.0000

Data Index: 299340 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1176. Min Act: -0.0001

Data Index: 1042835 (C4 (Web Text))

Max Activating Token Index: 594

Text #5

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1219. Min Act: -0.0001

Data Index: 278937 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1289. Min Act: -0.0001

Data Index: 512935 (C4 (Web Text))

Max Activating Token Index: 709

Text #7

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1275. Min Act: -0.0001

Data Index: 1244481 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1284. Min Act: -0.0000

Data Index: 1023901 (C4 (Web Text))

Max Activating Token Index: 956

Text #9

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1239. Min Act: -0.0001

Data Index: 82805 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1173. Min Act: -0.0000

Data Index: 989014 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1193. Min Act: -0.0000

Data Index: 527896 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1155. Min Act: -0.0000

Data Index: 936979 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1158. Min Act: -0.0000

Data Index: 1317318 (C4 (Web Text))

Max Activating Token Index: 701

Text #14

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1198. Min Act: -0.0001

Data Index: 891159 (C4 (Web Text))

Max Activating Token Index: 556

Text #15

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1233. Min Act: -0.0001

Data Index: 753144 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1152. Min Act: -0.0000

Data Index: 1062196 (C4 (Web Text))

Max Activating Token Index: 141

Text #17

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1133. Min Act: -0.0000

Data Index: 940266 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1121. Min Act: -0.0000

Data Index: 61114 (C4 (Web Text))

Max Activating Token Index: 641

Text #19

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1170. Min Act: -0.0001

Data Index: 1184393 (C4 (Web Text))

Max Activating Token Index: 46