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

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

Neuron 1236 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6391. Min Range: -2.6391

Max Act: 2.6391. Min Act: -0.0000

Data Index: 524490 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 2.6391. Min Range: -2.6391

Max Act: 2.5128. Min Act: -0.0000

Data Index: 79926 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 2.6391. Min Range: -2.6391

Max Act: 2.2392. Min Act: -0.0000

Data Index: 563458 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 2.6391. Min Range: -2.6391

Max Act: 2.2114. Min Act: -0.0000

Data Index: 817320 (C4 (Web Text))

Max Activating Token Index: 118

Text #4

Max Range: 2.6391. Min Range: -2.6391

Max Act: 2.1478. Min Act: -0.0000

Data Index: 591353 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 2.6391. Min Range: -2.6391

Max Act: 1.9474. Min Act: -0.0000

Data Index: 841381 (C4 (Web Text))

Max Activating Token Index: 561

Text #6

Max Range: 2.6391. Min Range: -2.6391

Max Act: 1.8317. Min Act: -0.0000

Data Index: 502567 (C4 (Web Text))

Max Activating Token Index: 945

Text #7

Max Range: 2.6391. Min Range: -2.6391

Max Act: 1.8166. Min Act: -0.0000

Data Index: 869278 (C4 (Web Text))

Max Activating Token Index: 205

Text #8

Max Range: 2.6391. Min Range: -2.6391

Max Act: 1.8956. Min Act: -0.0000

Data Index: 1177071 (C4 (Web Text))

Max Activating Token Index: 498

Text #9

Max Range: 2.6391. Min Range: -2.6391

Max Act: 1.9020. Min Act: -0.0000

Data Index: 1104618 (C4 (Web Text))

Max Activating Token Index: 399

Text #10

Max Range: 2.6391. Min Range: -2.6391

Max Act: 1.8822. Min Act: -0.0000

Data Index: 700278 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 2.6391. Min Range: -2.6391

Max Act: 1.8482. Min Act: -0.0000

Data Index: 529327 (C4 (Web Text))

Max Activating Token Index: 874

Text #12

Max Range: 2.6391. Min Range: -2.6391

Max Act: 1.9412. Min Act: -0.0000

Data Index: 1009834 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 2.6391. Min Range: -2.6391

Max Act: 1.7627. Min Act: -0.0000

Data Index: 663402 (C4 (Web Text))

Max Activating Token Index: 204

Text #14

Max Range: 2.6391. Min Range: -2.6391

Max Act: 1.7223. Min Act: -0.0000

Data Index: 802665 (C4 (Web Text))

Max Activating Token Index: 470

Text #15

Max Range: 2.6391. Min Range: -2.6391

Max Act: 1.9121. Min Act: -0.0000

Data Index: 75744 (C4 (Web Text))

Max Activating Token Index: 531

Text #16

Max Range: 2.6391. Min Range: -2.6391

Max Act: 1.7621. Min Act: -0.0000

Data Index: 223738 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 2.6391. Min Range: -2.6391

Max Act: 1.7407. Min Act: -0.0000

Data Index: 392792 (C4 (Web Text))

Max Activating Token Index: 195

Text #18

Max Range: 2.6391. Min Range: -2.6391

Max Act: 1.8280. Min Act: -0.0000

Data Index: 868722 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 2.6391. Min Range: -2.6391

Max Act: 1.7370. Min Act: -0.0000

Data Index: 123478 (C4 (Web Text))

Max Activating Token Index: 296