Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3703 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1914. Min Act: -0.0001

Data Index: 382259 (C4 (Web Text))

Max Activating Token Index: 501

Text #1

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1757. Min Act: -0.0001

Data Index: 1358427 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1749. Min Act: -0.0001

Data Index: 1069558 (C4 (Web Text))

Max Activating Token Index: 298

Text #3

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1572. Min Act: -0.0001

Data Index: 879770 (C4 (Web Text))

Max Activating Token Index: 700

Text #4

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1519. Min Act: -0.0001

Data Index: 801352 (C4 (Web Text))

Max Activating Token Index: 744

Text #5

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1664. Min Act: -0.0001

Data Index: 1180315 (C4 (Web Text))

Max Activating Token Index: 302

Text #6

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1549. Min Act: -0.0001

Data Index: 794964 (C4 (Web Text))

Max Activating Token Index: 1002

Text #7

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1399. Min Act: -0.0001

Data Index: 1307584 (C4 (Web Text))

Max Activating Token Index: 258

Text #8

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1359. Min Act: -0.0001

Data Index: 1107584 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1373. Min Act: -0.0001

Data Index: 937955 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1355. Min Act: -0.0001

Data Index: 719114 (C4 (Web Text))

Max Activating Token Index: 16

Text #11

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1299. Min Act: -0.0001

Data Index: 405942 (C4 (Web Text))

Max Activating Token Index: 410

Text #12

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1302. Min Act: -0.0001

Data Index: 642218 (C4 (Web Text))

Max Activating Token Index: 832

Text #13

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1298. Min Act: -0.0001

Data Index: 1327688 (C4 (Web Text))

Max Activating Token Index: 545

Text #14

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1258. Min Act: -0.0001

Data Index: 278991 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1342. Min Act: -0.0001

Data Index: 1338879 (C4 (Web Text))

Max Activating Token Index: 248

Text #16

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1289. Min Act: -0.0001

Data Index: 727986 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1245. Min Act: -0.0001

Data Index: 925799 (C4 (Web Text))

Max Activating Token Index: 415

Text #18

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1203. Min Act: -0.0001

Data Index: 658350 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1265. Min Act: -0.0001

Data Index: 870899 (C4 (Web Text))

Max Activating Token Index: 84