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

Dataset: The Pile

Neuron 2099 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2957. Min Act: -0.0000

Data Index: 599875 (The Pile)

Max Activating Token Index: 628

Text #1

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2735. Min Act: -0.0000

Data Index: 1507006 (The Pile)

Max Activating Token Index: 300

Text #2

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2318. Min Act: -0.0000

Data Index: 832680 (The Pile)

Max Activating Token Index: 275

Text #3

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2456. Min Act: -0.0000

Data Index: 501243 (The Pile)

Max Activating Token Index: 668

Text #4

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2296. Min Act: -0.0000

Data Index: 1696618 (The Pile)

Max Activating Token Index: 51

Text #5

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2439. Min Act: -0.0000

Data Index: 96654 (The Pile)

Max Activating Token Index: 314

Text #6

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2432. Min Act: -0.0000

Data Index: 1698756 (The Pile)

Max Activating Token Index: 90

Text #7

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2406. Min Act: -0.0000

Data Index: 1866634 (The Pile)

Max Activating Token Index: 730

Text #8

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2249. Min Act: -0.0000

Data Index: 104878 (The Pile)

Max Activating Token Index: 546

Text #9

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2312. Min Act: -0.0000

Data Index: 1240707 (The Pile)

Max Activating Token Index: 448

Text #10

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2350. Min Act: -0.0000

Data Index: 924006 (The Pile)

Max Activating Token Index: 523

Text #11

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2352. Min Act: -0.0000

Data Index: 316731 (The Pile)

Max Activating Token Index: 617

Text #12

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2543. Min Act: -0.0000

Data Index: 1688366 (The Pile)

Max Activating Token Index: 533

Text #13

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2336. Min Act: -0.0000

Data Index: 301252 (The Pile)

Max Activating Token Index: 382

Text #14

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2194. Min Act: -0.0000

Data Index: 546526 (The Pile)

Max Activating Token Index: 765

Text #15

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2343. Min Act: -0.0000

Data Index: 1130400 (The Pile)

Max Activating Token Index: 48

Text #16

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2237. Min Act: -0.0000

Data Index: 1008525 (The Pile)

Max Activating Token Index: 655

Text #17

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2353. Min Act: -0.0000

Data Index: 527559 (The Pile)

Max Activating Token Index: 457

Text #18

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2278. Min Act: -0.0000

Data Index: 1450548 (The Pile)

Max Activating Token Index: 763

Text #19

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2238. Min Act: -0.0000

Data Index: 1987529 (The Pile)

Max Activating Token Index: 690