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

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

Neuron 700 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4866. Min Range: -1.4866

Max Act: 1.4866. Min Act: -0.0002

Data Index: 1612603 (Python Code)

Max Activating Token Index: 13

Text #1

Max Range: 1.4866. Min Range: -1.4866

Max Act: 1.4817. Min Act: -0.0002

Data Index: 1410154 (Python Code)

Max Activating Token Index: 232

Text #2

Max Range: 1.4866. Min Range: -1.4866

Max Act: 1.3598. Min Act: -0.0002

Data Index: 1609337 (Python Code)

Max Activating Token Index: 139

Text #3

Max Range: 1.4866. Min Range: -1.4866

Max Act: 1.3094. Min Act: -0.0002

Data Index: 1597693 (Python Code)

Max Activating Token Index: 544

Text #4

Max Range: 1.4866. Min Range: -1.4866

Max Act: 1.3028. Min Act: -0.0002

Data Index: 1470277 (Python Code)

Max Activating Token Index: 494

Text #5

Max Range: 1.4866. Min Range: -1.4866

Max Act: 1.2537. Min Act: -0.0002

Data Index: 1436475 (Python Code)

Max Activating Token Index: 489

Text #6

Max Range: 1.4866. Min Range: -1.4866

Max Act: 1.2743. Min Act: -0.0002

Data Index: 1531897 (Python Code)

Max Activating Token Index: 198

Text #7

Max Range: 1.4866. Min Range: -1.4866

Max Act: 1.2335. Min Act: -0.0002

Data Index: 1483478 (Python Code)

Max Activating Token Index: 532

Text #8

Max Range: 1.4866. Min Range: -1.4866

Max Act: 1.3280. Min Act: -0.0002

Data Index: 1568596 (Python Code)

Max Activating Token Index: 652

Text #9

Max Range: 1.4866. Min Range: -1.4866

Max Act: 1.2026. Min Act: -0.0002

Data Index: 1580934 (Python Code)

Max Activating Token Index: 821

Text #10

Max Range: 1.4866. Min Range: -1.4866

Max Act: 1.1944. Min Act: -0.0002

Data Index: 1592244 (Python Code)

Max Activating Token Index: 268

Text #11

Max Range: 1.4866. Min Range: -1.4866

Max Act: 1.2346. Min Act: -0.0002

Data Index: 1437713 (Python Code)

Max Activating Token Index: 239

Text #12

Max Range: 1.4866. Min Range: -1.4866

Max Act: 1.2264. Min Act: -0.0002

Data Index: 1447659 (Python Code)

Max Activating Token Index: 545

Text #13

Max Range: 1.4866. Min Range: -1.4866

Max Act: 1.2504. Min Act: -0.0002

Data Index: 1643979 (Python Code)

Max Activating Token Index: 468

Text #14

Max Range: 1.4866. Min Range: -1.4866

Max Act: 1.2298. Min Act: -0.0002

Data Index: 1545613 (Python Code)

Max Activating Token Index: 65

Text #15

Max Range: 1.4866. Min Range: -1.4866

Max Act: 1.1921. Min Act: -0.0002

Data Index: 1374335 (Python Code)

Max Activating Token Index: 206

Text #16

Max Range: 1.4866. Min Range: -1.4866

Max Act: 1.1415. Min Act: -0.0002

Data Index: 1606244 (Python Code)

Max Activating Token Index: 770

Text #17

Max Range: 1.4866. Min Range: -1.4866

Max Act: 1.1627. Min Act: -0.0002

Data Index: 1642915 (Python Code)

Max Activating Token Index: 331

Text #18

Max Range: 1.4866. Min Range: -1.4866

Max Act: 1.1184. Min Act: -0.0002

Data Index: 1391707 (Python Code)

Max Activating Token Index: 351

Text #19

Max Range: 1.4866. Min Range: -1.4866

Max Act: 1.0896. Min Act: -0.0002

Data Index: 1443982 (Python Code)

Max Activating Token Index: 242