Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 196 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.5812. Min Range: -3.5812

Max Act: 3.5812. Min Act: -0.0000

Data Index: 1320788 (C4 (Web Text))

Max Activating Token Index: 991

Text #1

Max Range: 3.5812. Min Range: -3.5812

Max Act: 3.4006. Min Act: -0.0000

Data Index: 890949 (C4 (Web Text))

Max Activating Token Index: 491

Text #2

Max Range: 3.5812. Min Range: -3.5812

Max Act: 3.2335. Min Act: -0.0000

Data Index: 691101 (C4 (Web Text))

Max Activating Token Index: 477

Text #3

Max Range: 3.5812. Min Range: -3.5812

Max Act: 3.1821. Min Act: -0.0000

Data Index: 820148 (C4 (Web Text))

Max Activating Token Index: 487

Text #4

Max Range: 3.5812. Min Range: -3.5812

Max Act: 3.0473. Min Act: -0.0000

Data Index: 452532 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 3.5812. Min Range: -3.5812

Max Act: 3.1820. Min Act: -0.0000

Data Index: 248849 (C4 (Web Text))

Max Activating Token Index: 497

Text #6

Max Range: 3.5812. Min Range: -3.5812

Max Act: 3.3326. Min Act: -0.0000

Data Index: 466494 (C4 (Web Text))

Max Activating Token Index: 542

Text #7

Max Range: 3.5812. Min Range: -3.5812

Max Act: 3.3034. Min Act: -0.0000

Data Index: 470853 (C4 (Web Text))

Max Activating Token Index: 158

Text #8

Max Range: 3.5812. Min Range: -3.5812

Max Act: 3.2410. Min Act: -0.0000

Data Index: 1353910 (C4 (Web Text))

Max Activating Token Index: 83

Text #9

Max Range: 3.5812. Min Range: -3.5812

Max Act: 2.8213. Min Act: -0.0000

Data Index: 904900 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 3.5812. Min Range: -3.5812

Max Act: 3.2156. Min Act: -0.0000

Data Index: 868273 (C4 (Web Text))

Max Activating Token Index: 476

Text #11

Max Range: 3.5812. Min Range: -3.5812

Max Act: 3.0130. Min Act: -0.0000

Data Index: 796492 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 3.5812. Min Range: -3.5812

Max Act: 3.1585. Min Act: -0.0000

Data Index: 125343 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 3.5812. Min Range: -3.5812

Max Act: 3.0026. Min Act: -0.0000

Data Index: 733089 (C4 (Web Text))

Max Activating Token Index: 783

Text #14

Max Range: 3.5812. Min Range: -3.5812

Max Act: 2.9507. Min Act: -0.0000

Data Index: 637018 (C4 (Web Text))

Max Activating Token Index: 553

Text #15

Max Range: 3.5812. Min Range: -3.5812

Max Act: 3.0683. Min Act: -0.0000

Data Index: 1080090 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 3.5812. Min Range: -3.5812

Max Act: 3.0784. Min Act: -0.0000

Data Index: 1090513 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 3.5812. Min Range: -3.5812

Max Act: 2.8864. Min Act: -0.0000

Data Index: 565531 (C4 (Web Text))

Max Activating Token Index: 944

Text #18

Max Range: 3.5812. Min Range: -3.5812

Max Act: 3.0306. Min Act: -0.0000

Data Index: 486132 (C4 (Web Text))

Max Activating Token Index: 618

Text #19

Max Range: 3.5812. Min Range: -3.5812

Max Act: 2.6363. Min Act: -0.0000

Data Index: 140463 (C4 (Web Text))

Max Activating Token Index: 742