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

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

Neuron 4919 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2437. Min Range: -1.2437

Max Act: 1.2437. Min Act: -0.0000

Data Index: 1355432 (C4 (Web Text))

Max Activating Token Index: 898

Text #1

Max Range: 1.2437. Min Range: -1.2437

Max Act: 1.1920. Min Act: -0.0000

Data Index: 289965 (C4 (Web Text))

Max Activating Token Index: 870

Text #2

Max Range: 1.2437. Min Range: -1.2437

Max Act: 1.0320. Min Act: -0.0000

Data Index: 386345 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 1.2437. Min Range: -1.2437

Max Act: 1.0373. Min Act: -0.0000

Data Index: 1124419 (C4 (Web Text))

Max Activating Token Index: 758

Text #4

Max Range: 1.2437. Min Range: -1.2437

Max Act: 0.9337. Min Act: -0.0000

Data Index: 748450 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 1.2437. Min Range: -1.2437

Max Act: 0.9808. Min Act: -0.0000

Data Index: 1020128 (C4 (Web Text))

Max Activating Token Index: 415

Text #6

Max Range: 1.2437. Min Range: -1.2437

Max Act: 0.9468. Min Act: -0.0000

Data Index: 523817 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 1.2437. Min Range: -1.2437

Max Act: 1.0283. Min Act: -0.0000

Data Index: 1099763 (C4 (Web Text))

Max Activating Token Index: 874

Text #8

Max Range: 1.2437. Min Range: -1.2437

Max Act: 0.9184. Min Act: -0.0000

Data Index: 428940 (C4 (Web Text))

Max Activating Token Index: 441

Text #9

Max Range: 1.2437. Min Range: -1.2437

Max Act: 0.9461. Min Act: -0.0000

Data Index: 960478 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 1.2437. Min Range: -1.2437

Max Act: 0.9584. Min Act: -0.0000

Data Index: 502221 (C4 (Web Text))

Max Activating Token Index: 190

Text #11

Max Range: 1.2437. Min Range: -1.2437

Max Act: 0.9340. Min Act: -0.0000

Data Index: 1091600 (C4 (Web Text))

Max Activating Token Index: 826

Text #12

Max Range: 1.2437. Min Range: -1.2437

Max Act: 0.8747. Min Act: -0.0000

Data Index: 610543 (C4 (Web Text))

Max Activating Token Index: 215

Text #13

Max Range: 1.2437. Min Range: -1.2437

Max Act: 0.8573. Min Act: -0.0000

Data Index: 487459 (C4 (Web Text))

Max Activating Token Index: 541

Text #14

Max Range: 1.2437. Min Range: -1.2437

Max Act: 0.8736. Min Act: -0.0000

Data Index: 450760 (C4 (Web Text))

Max Activating Token Index: 544

Text #15

Max Range: 1.2437. Min Range: -1.2437

Max Act: 0.9220. Min Act: -0.0000

Data Index: 276749 (C4 (Web Text))

Max Activating Token Index: 398

Text #16

Max Range: 1.2437. Min Range: -1.2437

Max Act: 0.7938. Min Act: -0.0000

Data Index: 1236433 (C4 (Web Text))

Max Activating Token Index: 248

Text #17

Max Range: 1.2437. Min Range: -1.2437

Max Act: 0.8649. Min Act: -0.0000

Data Index: 475277 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 1.2437. Min Range: -1.2437

Max Act: 0.8257. Min Act: -0.0000

Data Index: 1062090 (C4 (Web Text))

Max Activating Token Index: 401

Text #19

Max Range: 1.2437. Min Range: -1.2437

Max Act: 0.7435. Min Act: -0.0000

Data Index: 15646 (C4 (Web Text))

Max Activating Token Index: 309