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

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

Neuron 2144 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1509. Min Act: -0.0001

Data Index: 1212894 (C4 (Web Text))

Max Activating Token Index: 277

Text #1

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1548. Min Act: -0.0001

Data Index: 453861 (C4 (Web Text))

Max Activating Token Index: 734

Text #2

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1370. Min Act: -0.0001

Data Index: 412553 (C4 (Web Text))

Max Activating Token Index: 350

Text #3

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1304. Min Act: -0.0001

Data Index: 1119310 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1324. Min Act: -0.0001

Data Index: 877984 (C4 (Web Text))

Max Activating Token Index: 363

Text #5

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1355. Min Act: -0.0001

Data Index: 1196767 (C4 (Web Text))

Max Activating Token Index: 964

Text #6

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1185. Min Act: -0.0001

Data Index: 453987 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1229. Min Act: -0.0001

Data Index: 1187652 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1136. Min Act: -0.0001

Data Index: 649177 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1331. Min Act: -0.0001

Data Index: 10808 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1292. Min Act: -0.0001

Data Index: 902307 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1310. Min Act: -0.0001

Data Index: 164261 (C4 (Web Text))

Max Activating Token Index: 83

Text #12

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1328. Min Act: -0.0001

Data Index: 276697 (C4 (Web Text))

Max Activating Token Index: 647

Text #13

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1247. Min Act: -0.0001

Data Index: 94703 (C4 (Web Text))

Max Activating Token Index: 336

Text #14

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1232. Min Act: -0.0001

Data Index: 1199318 (C4 (Web Text))

Max Activating Token Index: 730

Text #15

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1330. Min Act: -0.0001

Data Index: 939704 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1233. Min Act: -0.0001

Data Index: 1218099 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1236. Min Act: -0.0001

Data Index: 258677 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1106. Min Act: -0.0001

Data Index: 584635 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1189. Min Act: -0.0001

Data Index: 342108 (C4 (Web Text))

Max Activating Token Index: 574