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

Dataset: The Pile

Neuron 703 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2959. Min Act: -0.0000

Data Index: 1892600 (The Pile)

Max Activating Token Index: 331

Text #1

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2539. Min Act: -0.0000

Data Index: 854483 (The Pile)

Max Activating Token Index: 583

Text #2

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2759. Min Act: -0.0000

Data Index: 61466 (The Pile)

Max Activating Token Index: 1000

Text #3

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2457. Min Act: 0.0000

Data Index: 1162021 (The Pile)

Max Activating Token Index: 213

Text #4

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2330. Min Act: -0.0000

Data Index: 1998504 (The Pile)

Max Activating Token Index: 813

Text #5

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2475. Min Act: -0.0000

Data Index: 1434191 (The Pile)

Max Activating Token Index: 856

Text #6

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2354. Min Act: 0.0000

Data Index: 590083 (The Pile)

Max Activating Token Index: 816

Text #7

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2493. Min Act: -0.0000

Data Index: 1615810 (The Pile)

Max Activating Token Index: 290

Text #8

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2269. Min Act: -0.0000

Data Index: 1926609 (The Pile)

Max Activating Token Index: 577

Text #9

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2565. Min Act: -0.0000

Data Index: 1517590 (The Pile)

Max Activating Token Index: 963

Text #10

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2367. Min Act: -0.0000

Data Index: 1980746 (The Pile)

Max Activating Token Index: 292

Text #11

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2351. Min Act: -0.0000

Data Index: 1750734 (The Pile)

Max Activating Token Index: 426

Text #12

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2263. Min Act: -0.0000

Data Index: 1074036 (The Pile)

Max Activating Token Index: 367

Text #13

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2488. Min Act: -0.0000

Data Index: 946856 (The Pile)

Max Activating Token Index: 61

Text #14

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2508. Min Act: -0.0000

Data Index: 887347 (The Pile)

Max Activating Token Index: 994

Text #15

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2416. Min Act: -0.0000

Data Index: 136458 (The Pile)

Max Activating Token Index: 857

Text #16

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2386. Min Act: -0.0000

Data Index: 220168 (The Pile)

Max Activating Token Index: 938

Text #17

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2415. Min Act: -0.0000

Data Index: 1493327 (The Pile)

Max Activating Token Index: 931

Text #18

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2453. Min Act: -0.0000

Data Index: 1178476 (The Pile)

Max Activating Token Index: 873

Text #19

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2350. Min Act: -0.0000

Data Index: 1983798 (The Pile)

Max Activating Token Index: 848