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

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

Neuron 2540 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0438. Min Act: -0.0003

Data Index: 423689 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0397. Min Act: -0.0003

Data Index: 385752 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0410. Min Act: -0.0003

Data Index: 3680 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0389. Min Act: -0.0003

Data Index: 974642 (C4 (Web Text))

Max Activating Token Index: 677

Text #4

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0432. Min Act: -0.0003

Data Index: 357709 (C4 (Web Text))

Max Activating Token Index: 268

Text #5

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0410. Min Act: -0.0003

Data Index: 547945 (C4 (Web Text))

Max Activating Token Index: 833

Text #6

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0405. Min Act: -0.0003

Data Index: 653192 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0409. Min Act: -0.0003

Data Index: 396811 (C4 (Web Text))

Max Activating Token Index: 718

Text #8

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0381. Min Act: -0.0003

Data Index: 629060 (C4 (Web Text))

Max Activating Token Index: 946

Text #9

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0383. Min Act: -0.0003

Data Index: 859287 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0395. Min Act: -0.0003

Data Index: 963169 (C4 (Web Text))

Max Activating Token Index: 876

Text #11

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0349. Min Act: -0.0003

Data Index: 1248450 (C4 (Web Text))

Max Activating Token Index: 579

Text #12

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0383. Min Act: -0.0003

Data Index: 1154113 (C4 (Web Text))

Max Activating Token Index: 387

Text #13

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0355. Min Act: -0.0003

Data Index: 688462 (C4 (Web Text))

Max Activating Token Index: 412

Text #14

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0342. Min Act: -0.0003

Data Index: 678058 (C4 (Web Text))

Max Activating Token Index: 992

Text #15

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0362. Min Act: -0.0003

Data Index: 1272897 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0355. Min Act: -0.0003

Data Index: 1239942 (C4 (Web Text))

Max Activating Token Index: 606

Text #17

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0345. Min Act: -0.0003

Data Index: 1323858 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0342. Min Act: -0.0003

Data Index: 1217541 (C4 (Web Text))

Max Activating Token Index: 216

Text #19

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0352. Min Act: -0.0003

Data Index: 395102 (C4 (Web Text))

Max Activating Token Index: 38