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

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

Neuron 5824 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.6333. Min Act: -0.0000

Data Index: 42603 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.4396. Min Act: -0.0000

Data Index: 1124107 (C4 (Web Text))

Max Activating Token Index: 466

Text #2

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.1888. Min Act: -0.0000

Data Index: 1002243 (C4 (Web Text))

Max Activating Token Index: 765

Text #3

Max Range: 3.6333. Min Range: -3.6333

Max Act: 2.9735. Min Act: -0.0000

Data Index: 901682 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 3.6333. Min Range: -3.6333

Max Act: 2.6044. Min Act: -0.0000

Data Index: 1348078 (C4 (Web Text))

Max Activating Token Index: 410

Text #5

Max Range: 3.6333. Min Range: -3.6333

Max Act: 2.2136. Min Act: -0.0000

Data Index: 636734 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 3.6333. Min Range: -3.6333

Max Act: 2.3997. Min Act: -0.0000

Data Index: 1339406 (C4 (Web Text))

Max Activating Token Index: 609

Text #7

Max Range: 3.6333. Min Range: -3.6333

Max Act: 2.2233. Min Act: -0.0000

Data Index: 1197957 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 3.6333. Min Range: -3.6333

Max Act: 2.4367. Min Act: -0.0000

Data Index: 166793 (C4 (Web Text))

Max Activating Token Index: 429

Text #9

Max Range: 3.6333. Min Range: -3.6333

Max Act: 2.2168. Min Act: -0.0000

Data Index: 341281 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 3.6333. Min Range: -3.6333

Max Act: 2.4275. Min Act: -0.0000

Data Index: 735936 (C4 (Web Text))

Max Activating Token Index: 266

Text #11

Max Range: 3.6333. Min Range: -3.6333

Max Act: 2.1315. Min Act: -0.0000

Data Index: 369393 (C4 (Web Text))

Max Activating Token Index: 674

Text #12

Max Range: 3.6333. Min Range: -3.6333

Max Act: 2.3268. Min Act: -0.0000

Data Index: 136730 (C4 (Web Text))

Max Activating Token Index: 998

Text #13

Max Range: 3.6333. Min Range: -3.6333

Max Act: 2.1939. Min Act: -0.0000

Data Index: 789401 (C4 (Web Text))

Max Activating Token Index: 749

Text #14

Max Range: 3.6333. Min Range: -3.6333

Max Act: 2.1756. Min Act: -0.0000

Data Index: 248323 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 3.6333. Min Range: -3.6333

Max Act: 2.1761. Min Act: -0.0000

Data Index: 504311 (C4 (Web Text))

Max Activating Token Index: 636

Text #16

Max Range: 3.6333. Min Range: -3.6333

Max Act: 2.1422. Min Act: -0.0000

Data Index: 160514 (C4 (Web Text))

Max Activating Token Index: 741

Text #17

Max Range: 3.6333. Min Range: -3.6333

Max Act: 2.0224. Min Act: -0.0000

Data Index: 88411 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 3.6333. Min Range: -3.6333

Max Act: 2.0068. Min Act: -0.0000

Data Index: 1057442 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 3.6333. Min Range: -3.6333

Max Act: 2.2393. Min Act: -0.0000

Data Index: 1242088 (C4 (Web Text))

Max Activating Token Index: 76