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

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

Neuron 1649 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1427. Min Act: -0.0002

Data Index: 299744 (C4 (Web Text))

Max Activating Token Index: 401

Text #1

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1467. Min Act: -0.0002

Data Index: 968544 (C4 (Web Text))

Max Activating Token Index: 247

Text #2

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1473. Min Act: -0.0002

Data Index: 215347 (C4 (Web Text))

Max Activating Token Index: 460

Text #3

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1475. Min Act: -0.0002

Data Index: 950668 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1390. Min Act: -0.0002

Data Index: 558978 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1319. Min Act: -0.0002

Data Index: 631283 (C4 (Web Text))

Max Activating Token Index: 811

Text #6

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1283. Min Act: -0.0002

Data Index: 761671 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1348. Min Act: -0.0002

Data Index: 524184 (C4 (Web Text))

Max Activating Token Index: 596

Text #8

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1274. Min Act: -0.0002

Data Index: 1351329 (C4 (Web Text))

Max Activating Token Index: 962

Text #9

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1312. Min Act: -0.0002

Data Index: 439214 (C4 (Web Text))

Max Activating Token Index: 228

Text #10

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1085. Min Act: -0.0002

Data Index: 975117 (C4 (Web Text))

Max Activating Token Index: 788

Text #11

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1280. Min Act: -0.0002

Data Index: 1210262 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1133. Min Act: -0.0002

Data Index: 330927 (C4 (Web Text))

Max Activating Token Index: 514

Text #13

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1156. Min Act: -0.0002

Data Index: 718321 (C4 (Web Text))

Max Activating Token Index: 660

Text #14

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1208. Min Act: -0.0002

Data Index: 254471 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.0966. Min Act: -0.0002

Data Index: 718484 (C4 (Web Text))

Max Activating Token Index: 829

Text #16

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1124. Min Act: -0.0002

Data Index: 282982 (C4 (Web Text))

Max Activating Token Index: 536

Text #17

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1099. Min Act: -0.0002

Data Index: 16258 (C4 (Web Text))

Max Activating Token Index: 54

Text #18

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1024. Min Act: -0.0002

Data Index: 1341211 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1031. Min Act: -0.0002

Data Index: 172703 (C4 (Web Text))

Max Activating Token Index: 994