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

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

Neuron 3517 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: 3.5385. Min Range: -3.5385

Max Act: 3.5385. Min Act: -0.0000

Data Index: 775855 (C4 (Web Text))

Max Activating Token Index: 823

Text #1

Max Range: 3.5385. Min Range: -3.5385

Max Act: 3.1658. Min Act: -0.0000

Data Index: 371955 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 3.5385. Min Range: -3.5385

Max Act: 2.9346. Min Act: -0.0000

Data Index: 765854 (C4 (Web Text))

Max Activating Token Index: 504

Text #3

Max Range: 3.5385. Min Range: -3.5385

Max Act: 2.6908. Min Act: -0.0000

Data Index: 1089332 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 3.5385. Min Range: -3.5385

Max Act: 2.5158. Min Act: -0.0000

Data Index: 1190107 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 3.5385. Min Range: -3.5385

Max Act: 2.3069. Min Act: -0.0000

Data Index: 1160641 (C4 (Web Text))

Max Activating Token Index: 252

Text #6

Max Range: 3.5385. Min Range: -3.5385

Max Act: 2.2922. Min Act: -0.0000

Data Index: 1086782 (C4 (Web Text))

Max Activating Token Index: 869

Text #7

Max Range: 3.5385. Min Range: -3.5385

Max Act: 2.1407. Min Act: -0.0000

Data Index: 1180612 (C4 (Web Text))

Max Activating Token Index: 879

Text #8

Max Range: 3.5385. Min Range: -3.5385

Max Act: 2.0734. Min Act: -0.0000

Data Index: 188303 (C4 (Web Text))

Max Activating Token Index: 306

Text #9

Max Range: 3.5385. Min Range: -3.5385

Max Act: 2.1718. Min Act: -0.0000

Data Index: 871483 (C4 (Web Text))

Max Activating Token Index: 268

Text #10

Max Range: 3.5385. Min Range: -3.5385

Max Act: 1.9631. Min Act: -0.0000

Data Index: 518738 (C4 (Web Text))

Max Activating Token Index: 797

Text #11

Max Range: 3.5385. Min Range: -3.5385

Max Act: 2.0578. Min Act: -0.0000

Data Index: 596194 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 3.5385. Min Range: -3.5385

Max Act: 2.1733. Min Act: -0.0000

Data Index: 304770 (C4 (Web Text))

Max Activating Token Index: 337

Text #13

Max Range: 3.5385. Min Range: -3.5385

Max Act: 2.0464. Min Act: -0.0000

Data Index: 929344 (C4 (Web Text))

Max Activating Token Index: 477

Text #14

Max Range: 3.5385. Min Range: -3.5385

Max Act: 2.0267. Min Act: -0.0000

Data Index: 778038 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 3.5385. Min Range: -3.5385

Max Act: 2.0144. Min Act: -0.0000

Data Index: 271865 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 3.5385. Min Range: -3.5385

Max Act: 2.0646. Min Act: -0.0000

Data Index: 1229460 (C4 (Web Text))

Max Activating Token Index: 839

Text #17

Max Range: 3.5385. Min Range: -3.5385

Max Act: 1.9227. Min Act: -0.0000

Data Index: 999286 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 3.5385. Min Range: -3.5385

Max Act: 1.9335. Min Act: -0.0000

Data Index: 1220191 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 3.5385. Min Range: -3.5385

Max Act: 1.8855. Min Act: -0.0000

Data Index: 80630 (C4 (Web Text))

Max Activating Token Index: 189