Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1374 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3545. Min Range: -0.3545

Max Act: 0.3545. Min Act: -0.0001

Data Index: 1406995 (Python Code)

Max Activating Token Index: 288

Text #1

Max Range: 0.3545. Min Range: -0.3545

Max Act: 0.2814. Min Act: 0.0000

Data Index: 1478485 (Python Code)

Max Activating Token Index: 373

Text #2

Max Range: 0.3545. Min Range: -0.3545

Max Act: 0.2638. Min Act: -0.0000

Data Index: 1397370 (Python Code)

Max Activating Token Index: 615

Text #3

Max Range: 0.3545. Min Range: -0.3545

Max Act: 0.2531. Min Act: -0.0000

Data Index: 1524468 (Python Code)

Max Activating Token Index: 718

Text #4

Max Range: 0.3545. Min Range: -0.3545

Max Act: 0.2579. Min Act: -0.0000

Data Index: 1468699 (Python Code)

Max Activating Token Index: 560

Text #5

Max Range: 0.3545. Min Range: -0.3545

Max Act: 0.2597. Min Act: 0.0000

Data Index: 1603216 (Python Code)

Max Activating Token Index: 331

Text #6

Max Range: 0.3545. Min Range: -0.3545

Max Act: 0.2580. Min Act: 0.0000

Data Index: 1514301 (Python Code)

Max Activating Token Index: 903

Text #7

Max Range: 0.3545. Min Range: -0.3545

Max Act: 0.2527. Min Act: -0.0001

Data Index: 1638339 (Python Code)

Max Activating Token Index: 30

Text #8

Max Range: 0.3545. Min Range: -0.3545

Max Act: 0.2502. Min Act: 0.0002

Data Index: 1572608 (Python Code)

Max Activating Token Index: 793

Text #9

Max Range: 0.3545. Min Range: -0.3545

Max Act: 0.2299. Min Act: 0.0001

Data Index: 1571983 (Python Code)

Max Activating Token Index: 231

Text #10

Max Range: 0.3545. Min Range: -0.3545

Max Act: 0.2565. Min Act: -0.0000

Data Index: 1414197 (Python Code)

Max Activating Token Index: 31

Text #11

Max Range: 0.3545. Min Range: -0.3545

Max Act: 0.2427. Min Act: -0.0001

Data Index: 1370642 (Python Code)

Max Activating Token Index: 206

Text #12

Max Range: 0.3545. Min Range: -0.3545

Max Act: 0.2358. Min Act: -0.0001

Data Index: 1612943 (Python Code)

Max Activating Token Index: 132

Text #13

Max Range: 0.3545. Min Range: -0.3545

Max Act: 0.2385. Min Act: -0.0000

Data Index: 1435695 (Python Code)

Max Activating Token Index: 124

Text #14

Max Range: 0.3545. Min Range: -0.3545

Max Act: 0.2453. Min Act: -0.0000

Data Index: 1604588 (Python Code)

Max Activating Token Index: 909

Text #15

Max Range: 0.3545. Min Range: -0.3545

Max Act: 0.2198. Min Act: -0.0000

Data Index: 1502342 (Python Code)

Max Activating Token Index: 755

Text #16

Max Range: 0.3545. Min Range: -0.3545

Max Act: 0.2393. Min Act: -0.0001

Data Index: 1428039 (Python Code)

Max Activating Token Index: 400

Text #17

Max Range: 0.3545. Min Range: -0.3545

Max Act: 0.2463. Min Act: -0.0000

Data Index: 1381192 (Python Code)

Max Activating Token Index: 992

Text #18

Max Range: 0.3545. Min Range: -0.3545

Max Act: 0.2464. Min Act: -0.0000

Data Index: 1362962 (Python Code)

Max Activating Token Index: 893

Text #19

Max Range: 0.3545. Min Range: -0.3545

Max Act: 0.2434. Min Act: -0.0000

Data Index: 1382314 (Python Code)

Max Activating Token Index: 367