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

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

Neuron 907 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9351. Min Range: -4.9351

Max Act: 4.9351. Min Act: -0.0000

Data Index: 1492666 (Python Code)

Max Activating Token Index: 215

Text #1

Max Range: 4.9351. Min Range: -4.9351

Max Act: 4.8598. Min Act: -0.0000

Data Index: 1575362 (Python Code)

Max Activating Token Index: 404

Text #2

Max Range: 4.9351. Min Range: -4.9351

Max Act: 4.4943. Min Act: -0.0000

Data Index: 1631704 (Python Code)

Max Activating Token Index: 1003

Text #3

Max Range: 4.9351. Min Range: -4.9351

Max Act: 4.1638. Min Act: -0.0000

Data Index: 1657082 (Python Code)

Max Activating Token Index: 665

Text #4

Max Range: 4.9351. Min Range: -4.9351

Max Act: 3.6458. Min Act: -0.0000

Data Index: 1425662 (Python Code)

Max Activating Token Index: 918

Text #5

Max Range: 4.9351. Min Range: -4.9351

Max Act: 4.2947. Min Act: -0.0000

Data Index: 1580764 (Python Code)

Max Activating Token Index: 748

Text #6

Max Range: 4.9351. Min Range: -4.9351

Max Act: 3.7516. Min Act: -0.0000

Data Index: 1527754 (Python Code)

Max Activating Token Index: 900

Text #7

Max Range: 4.9351. Min Range: -4.9351

Max Act: 3.8039. Min Act: -0.0000

Data Index: 1502677 (Python Code)

Max Activating Token Index: 959

Text #8

Max Range: 4.9351. Min Range: -4.9351

Max Act: 4.2798. Min Act: -0.0000

Data Index: 1491434 (Python Code)

Max Activating Token Index: 923

Text #9

Max Range: 4.9351. Min Range: -4.9351

Max Act: 4.0900. Min Act: -0.0000

Data Index: 1612516 (Python Code)

Max Activating Token Index: 946

Text #10

Max Range: 4.9351. Min Range: -4.9351

Max Act: 3.7105. Min Act: -0.0000

Data Index: 1432150 (Python Code)

Max Activating Token Index: 958

Text #11

Max Range: 4.9351. Min Range: -4.9351

Max Act: 4.0376. Min Act: -0.0000

Data Index: 1610802 (Python Code)

Max Activating Token Index: 740

Text #12

Max Range: 4.9351. Min Range: -4.9351

Max Act: 3.8563. Min Act: -0.0000

Data Index: 1373823 (Python Code)

Max Activating Token Index: 1013

Text #13

Max Range: 4.9351. Min Range: -4.9351

Max Act: 3.8361. Min Act: -0.0000

Data Index: 1499930 (Python Code)

Max Activating Token Index: 839

Text #14

Max Range: 4.9351. Min Range: -4.9351

Max Act: 4.0567. Min Act: -0.0000

Data Index: 1575563 (Python Code)

Max Activating Token Index: 964

Text #15

Max Range: 4.9351. Min Range: -4.9351

Max Act: 4.1848. Min Act: -0.0000

Data Index: 1533499 (Python Code)

Max Activating Token Index: 1003

Text #16

Max Range: 4.9351. Min Range: -4.9351

Max Act: 4.0228. Min Act: -0.0000

Data Index: 1619521 (Python Code)

Max Activating Token Index: 798

Text #17

Max Range: 4.9351. Min Range: -4.9351

Max Act: 4.0990. Min Act: -0.0000

Data Index: 1618179 (Python Code)

Max Activating Token Index: 887

Text #18

Max Range: 4.9351. Min Range: -4.9351

Max Act: 3.7640. Min Act: -0.0000

Data Index: 1372226 (Python Code)

Max Activating Token Index: 934

Text #19

Max Range: 4.9351. Min Range: -4.9351

Max Act: 4.0534. Min Act: -0.0000

Data Index: 1531393 (Python Code)

Max Activating Token Index: 1004