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

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

Neuron 326 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.4383. Min Range: -6.4383

Max Act: 6.4383. Min Act: -0.0000

Data Index: 582680 (C4 (Web Text))

Max Activating Token Index: 219

Text #1

Max Range: 6.4383. Min Range: -6.4383

Max Act: 4.4475. Min Act: -0.0000

Data Index: 1054934 (C4 (Web Text))

Max Activating Token Index: 338

Text #2

Max Range: 6.4383. Min Range: -6.4383

Max Act: 4.6719. Min Act: -0.0000

Data Index: 422515 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 6.4383. Min Range: -6.4383

Max Act: 4.2754. Min Act: -0.0000

Data Index: 571329 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 6.4383. Min Range: -6.4383

Max Act: 4.0208. Min Act: -0.0000

Data Index: 463700 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 6.4383. Min Range: -6.4383

Max Act: 4.1655. Min Act: -0.0000

Data Index: 286487 (C4 (Web Text))

Max Activating Token Index: 326

Text #6

Max Range: 6.4383. Min Range: -6.4383

Max Act: 4.1592. Min Act: -0.0000

Data Index: 79679 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 6.4383. Min Range: -6.4383

Max Act: 4.2656. Min Act: -0.0000

Data Index: 849931 (C4 (Web Text))

Max Activating Token Index: 583

Text #8

Max Range: 6.4383. Min Range: -6.4383

Max Act: 4.0927. Min Act: -0.0000

Data Index: 1250155 (C4 (Web Text))

Max Activating Token Index: 561

Text #9

Max Range: 6.4383. Min Range: -6.4383

Max Act: 4.0662. Min Act: -0.0000

Data Index: 1206080 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 6.4383. Min Range: -6.4383

Max Act: 4.0481. Min Act: -0.0000

Data Index: 205898 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 6.4383. Min Range: -6.4383

Max Act: 4.1378. Min Act: -0.0000

Data Index: 640131 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 6.4383. Min Range: -6.4383

Max Act: 3.3061. Min Act: -0.0000

Data Index: 677584 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 6.4383. Min Range: -6.4383

Max Act: 3.7066. Min Act: -0.0000

Data Index: 102161 (C4 (Web Text))

Max Activating Token Index: 590

Text #14

Max Range: 6.4383. Min Range: -6.4383

Max Act: 4.1328. Min Act: -0.0000

Data Index: 450564 (C4 (Web Text))

Max Activating Token Index: 116

Text #15

Max Range: 6.4383. Min Range: -6.4383

Max Act: 4.1193. Min Act: -0.0001

Data Index: 429452 (C4 (Web Text))

Max Activating Token Index: 318

Text #16

Max Range: 6.4383. Min Range: -6.4383

Max Act: 3.6225. Min Act: -0.0000

Data Index: 1223112 (C4 (Web Text))

Max Activating Token Index: 966

Text #17

Max Range: 6.4383. Min Range: -6.4383

Max Act: 3.9600. Min Act: -0.0000

Data Index: 719324 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 6.4383. Min Range: -6.4383

Max Act: 3.9880. Min Act: -0.0000

Data Index: 1006451 (C4 (Web Text))

Max Activating Token Index: 706

Text #19

Max Range: 6.4383. Min Range: -6.4383

Max Act: 3.7228. Min Act: -0.0000

Data Index: 863241 (C4 (Web Text))

Max Activating Token Index: 822