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

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

Neuron 3993 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.4969. Min Act: -0.0002

Data Index: 798441 (C4 (Web Text))

Max Activating Token Index: 1004

Text #1

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.3755. Min Act: -0.0001

Data Index: 699074 (C4 (Web Text))

Max Activating Token Index: 301

Text #2

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.3501. Min Act: -0.0001

Data Index: 1175109 (C4 (Web Text))

Max Activating Token Index: 211

Text #3

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.3428. Min Act: -0.0001

Data Index: 228674 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.2715. Min Act: -0.0002

Data Index: 207402 (C4 (Web Text))

Max Activating Token Index: 1003

Text #5

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.3370. Min Act: -0.0002

Data Index: 109255 (C4 (Web Text))

Max Activating Token Index: 431

Text #6

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.3255. Min Act: -0.0001

Data Index: 205007 (C4 (Web Text))

Max Activating Token Index: 293

Text #7

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.2536. Min Act: -0.0001

Data Index: 1116293 (C4 (Web Text))

Max Activating Token Index: 615

Text #8

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.2194. Min Act: -0.0002

Data Index: 1058458 (C4 (Web Text))

Max Activating Token Index: 826

Text #9

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.3301. Min Act: -0.0002

Data Index: 133790 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.2516. Min Act: -0.0002

Data Index: 1007711 (C4 (Web Text))

Max Activating Token Index: 281

Text #11

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.2423. Min Act: -0.0001

Data Index: 519564 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.2664. Min Act: -0.0001

Data Index: 867562 (C4 (Web Text))

Max Activating Token Index: 442

Text #13

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.2602. Min Act: -0.0002

Data Index: 816160 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.2336. Min Act: -0.0002

Data Index: 1095446 (C4 (Web Text))

Max Activating Token Index: 907

Text #15

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.2589. Min Act: -0.0001

Data Index: 282901 (C4 (Web Text))

Max Activating Token Index: 967

Text #16

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.2280. Min Act: -0.0001

Data Index: 1130431 (C4 (Web Text))

Max Activating Token Index: 73

Text #17

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.2234. Min Act: -0.0001

Data Index: 582495 (C4 (Web Text))

Max Activating Token Index: 943

Text #18

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.2518. Min Act: -0.0002

Data Index: 1293456 (C4 (Web Text))

Max Activating Token Index: 417

Text #19

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.2508. Min Act: -0.0001

Data Index: 365823 (C4 (Web Text))

Max Activating Token Index: 979