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

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

Neuron 3298 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9523. Min Range: -1.9523

Max Act: 1.9523. Min Act: -0.0000

Data Index: 348511 (C4 (Web Text))

Max Activating Token Index: 937

Text #1

Max Range: 1.9523. Min Range: -1.9523

Max Act: 1.0586. Min Act: -0.0000

Data Index: 878847 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 1.9523. Min Range: -1.9523

Max Act: 1.3981. Min Act: -0.0000

Data Index: 818419 (C4 (Web Text))

Max Activating Token Index: 688

Text #3

Max Range: 1.9523. Min Range: -1.9523

Max Act: 1.0115. Min Act: -0.0000

Data Index: 1335750 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 1.9523. Min Range: -1.9523

Max Act: 1.1423. Min Act: -0.0000

Data Index: 1277949 (C4 (Web Text))

Max Activating Token Index: 302

Text #5

Max Range: 1.9523. Min Range: -1.9523

Max Act: 0.9407. Min Act: -0.0000

Data Index: 70714 (C4 (Web Text))

Max Activating Token Index: 558

Text #6

Max Range: 1.9523. Min Range: -1.9523

Max Act: 0.6321. Min Act: -0.0000

Data Index: 154977 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 1.9523. Min Range: -1.9523

Max Act: 0.6103. Min Act: -0.0000

Data Index: 490751 (C4 (Web Text))

Max Activating Token Index: 870

Text #8

Max Range: 1.9523. Min Range: -1.9523

Max Act: 0.6620. Min Act: -0.0000

Data Index: 1301574 (C4 (Web Text))

Max Activating Token Index: 745

Text #9

Max Range: 1.9523. Min Range: -1.9523

Max Act: 0.4880. Min Act: -0.0000

Data Index: 42348 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 1.9523. Min Range: -1.9523

Max Act: 0.4911. Min Act: -0.0000

Data Index: 467881 (C4 (Web Text))

Max Activating Token Index: 503

Text #11

Max Range: 1.9523. Min Range: -1.9523

Max Act: 0.4783. Min Act: -0.0000

Data Index: 663396 (C4 (Web Text))

Max Activating Token Index: 683

Text #12

Max Range: 1.9523. Min Range: -1.9523

Max Act: 0.5279. Min Act: -0.0000

Data Index: 948578 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 1.9523. Min Range: -1.9523

Max Act: 0.4595. Min Act: -0.0000

Data Index: 1189339 (C4 (Web Text))

Max Activating Token Index: 769

Text #14

Max Range: 1.9523. Min Range: -1.9523

Max Act: 0.4498. Min Act: -0.0000

Data Index: 744438 (C4 (Web Text))

Max Activating Token Index: 709

Text #15

Max Range: 1.9523. Min Range: -1.9523

Max Act: 0.4457. Min Act: -0.0000

Data Index: 892204 (C4 (Web Text))

Max Activating Token Index: 336

Text #16

Max Range: 1.9523. Min Range: -1.9523

Max Act: 0.4355. Min Act: -0.0000

Data Index: 110828 (C4 (Web Text))

Max Activating Token Index: 313

Text #17

Max Range: 1.9523. Min Range: -1.9523

Max Act: 0.4684. Min Act: -0.0000

Data Index: 897961 (C4 (Web Text))

Max Activating Token Index: 1012

Text #18

Max Range: 1.9523. Min Range: -1.9523

Max Act: 0.4195. Min Act: -0.0000

Data Index: 344352 (C4 (Web Text))

Max Activating Token Index: 477

Text #19

Max Range: 1.9523. Min Range: -1.9523

Max Act: 0.4264. Min Act: -0.0000

Data Index: 1099038 (C4 (Web Text))

Max Activating Token Index: 412