Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2834 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.3464. Min Act: -0.0000

Data Index: 761478 (C4 (Web Text))

Max Activating Token Index: 767

Text #1

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2727. Min Act: -0.0000

Data Index: 1144894 (C4 (Web Text))

Max Activating Token Index: 985

Text #2

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2411. Min Act: -0.0000

Data Index: 1627200 (Python Code)

Max Activating Token Index: 343

Text #3

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2439. Min Act: -0.0000

Data Index: 1207049 (C4 (Web Text))

Max Activating Token Index: 634

Text #4

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2347. Min Act: -0.0000

Data Index: 524192 (C4 (Web Text))

Max Activating Token Index: 839

Text #5

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2396. Min Act: -0.0000

Data Index: 989517 (C4 (Web Text))

Max Activating Token Index: 579

Text #6

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2310. Min Act: -0.0000

Data Index: 1567530 (Python Code)

Max Activating Token Index: 339

Text #7

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2199. Min Act: -0.0000

Data Index: 1429377 (Python Code)

Max Activating Token Index: 626

Text #8

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2629. Min Act: -0.0000

Data Index: 1473785 (Python Code)

Max Activating Token Index: 1004

Text #9

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2481. Min Act: -0.0000

Data Index: 1482598 (Python Code)

Max Activating Token Index: 579

Text #10

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2188. Min Act: -0.0000

Data Index: 1609910 (Python Code)

Max Activating Token Index: 1020

Text #11

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2259. Min Act: -0.0000

Data Index: 1575964 (Python Code)

Max Activating Token Index: 405

Text #12

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2405. Min Act: -0.0000

Data Index: 1498136 (Python Code)

Max Activating Token Index: 249

Text #13

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2342. Min Act: -0.0000

Data Index: 1509558 (Python Code)

Max Activating Token Index: 104

Text #14

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2332. Min Act: -0.0000

Data Index: 1581938 (Python Code)

Max Activating Token Index: 343

Text #15

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2193. Min Act: -0.0000

Data Index: 1438704 (Python Code)

Max Activating Token Index: 750

Text #16

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2393. Min Act: -0.0000

Data Index: 806872 (C4 (Web Text))

Max Activating Token Index: 722

Text #17

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2289. Min Act: -0.0000

Data Index: 1382824 (Python Code)

Max Activating Token Index: 943

Text #18

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2301. Min Act: -0.0000

Data Index: 1615578 (Python Code)

Max Activating Token Index: 1004

Text #19

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2261. Min Act: -0.0000

Data Index: 1602378 (Python Code)

Max Activating Token Index: 645