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

Dataset: The Pile

Neuron 2067 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: 0.2745. Min Range: -0.2745

Max Act: 0.2745. Min Act: -0.0000

Data Index: 889617 (The Pile)

Max Activating Token Index: 779

Text #1

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2577. Min Act: -0.0000

Data Index: 233835 (The Pile)

Max Activating Token Index: 668

Text #2

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2647. Min Act: -0.0000

Data Index: 1128030 (The Pile)

Max Activating Token Index: 462

Text #3

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2606. Min Act: -0.0000

Data Index: 386140 (The Pile)

Max Activating Token Index: 788

Text #4

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2330. Min Act: -0.0000

Data Index: 1975093 (The Pile)

Max Activating Token Index: 765

Text #5

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2626. Min Act: -0.0000

Data Index: 1427146 (The Pile)

Max Activating Token Index: 884

Text #6

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2317. Min Act: -0.0000

Data Index: 3290 (The Pile)

Max Activating Token Index: 534

Text #7

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2643. Min Act: -0.0000

Data Index: 1274298 (The Pile)

Max Activating Token Index: 161

Text #8

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2534. Min Act: -0.0000

Data Index: 385033 (The Pile)

Max Activating Token Index: 723

Text #9

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2632. Min Act: -0.0000

Data Index: 1515304 (The Pile)

Max Activating Token Index: 617

Text #10

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2422. Min Act: -0.0000

Data Index: 1765886 (The Pile)

Max Activating Token Index: 717

Text #11

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2252. Min Act: -0.0000

Data Index: 1106829 (The Pile)

Max Activating Token Index: 459

Text #12

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2349. Min Act: -0.0000

Data Index: 1333885 (The Pile)

Max Activating Token Index: 443

Text #13

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2301. Min Act: -0.0000

Data Index: 1215484 (The Pile)

Max Activating Token Index: 872

Text #14

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2297. Min Act: -0.0000

Data Index: 191977 (The Pile)

Max Activating Token Index: 511

Text #15

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2136. Min Act: -0.0000

Data Index: 1042461 (The Pile)

Max Activating Token Index: 484

Text #16

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2366. Min Act: -0.0000

Data Index: 1185580 (The Pile)

Max Activating Token Index: 399

Text #17

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2173. Min Act: -0.0000

Data Index: 612595 (The Pile)

Max Activating Token Index: 796

Text #18

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2125. Min Act: -0.0000

Data Index: 1675226 (The Pile)

Max Activating Token Index: 649

Text #19

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2128. Min Act: -0.0000

Data Index: 89443 (The Pile)

Max Activating Token Index: 613