Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3256 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.3985. Min Range: -0.3985

Max Act: 0.3985. Min Act: -0.0000

Data Index: 715875 (The Pile)

Max Activating Token Index: 135

Text #1

Max Range: 0.3985. Min Range: -0.3985

Max Act: 0.3723. Min Act: -0.0000

Data Index: 598168 (The Pile)

Max Activating Token Index: 426

Text #2

Max Range: 0.3985. Min Range: -0.3985

Max Act: 0.3693. Min Act: -0.0000

Data Index: 1971954 (The Pile)

Max Activating Token Index: 966

Text #3

Max Range: 0.3985. Min Range: -0.3985

Max Act: 0.3672. Min Act: -0.0000

Data Index: 758700 (The Pile)

Max Activating Token Index: 595

Text #4

Max Range: 0.3985. Min Range: -0.3985

Max Act: 0.3624. Min Act: -0.0000

Data Index: 1882154 (The Pile)

Max Activating Token Index: 532

Text #5

Max Range: 0.3985. Min Range: -0.3985

Max Act: 0.3251. Min Act: -0.0000

Data Index: 1118100 (The Pile)

Max Activating Token Index: 884

Text #6

Max Range: 0.3985. Min Range: -0.3985

Max Act: 0.3369. Min Act: -0.0000

Data Index: 50528 (The Pile)

Max Activating Token Index: 318

Text #7

Max Range: 0.3985. Min Range: -0.3985

Max Act: 0.3589. Min Act: -0.0000

Data Index: 1451882 (The Pile)

Max Activating Token Index: 147

Text #8

Max Range: 0.3985. Min Range: -0.3985

Max Act: 0.3310. Min Act: -0.0000

Data Index: 762545 (The Pile)

Max Activating Token Index: 423

Text #9

Max Range: 0.3985. Min Range: -0.3985

Max Act: 0.3367. Min Act: -0.0000

Data Index: 1043830 (The Pile)

Max Activating Token Index: 132

Text #10

Max Range: 0.3985. Min Range: -0.3985

Max Act: 0.3234. Min Act: -0.0000

Data Index: 28286 (The Pile)

Max Activating Token Index: 229

Text #11

Max Range: 0.3985. Min Range: -0.3985

Max Act: 0.3055. Min Act: -0.0000

Data Index: 1789232 (The Pile)

Max Activating Token Index: 752

Text #12

Max Range: 0.3985. Min Range: -0.3985

Max Act: 0.3043. Min Act: -0.0000

Data Index: 988695 (The Pile)

Max Activating Token Index: 124

Text #13

Max Range: 0.3985. Min Range: -0.3985

Max Act: 0.3263. Min Act: -0.0000

Data Index: 1453863 (The Pile)

Max Activating Token Index: 869

Text #14

Max Range: 0.3985. Min Range: -0.3985

Max Act: 0.3169. Min Act: -0.0000

Data Index: 1697233 (The Pile)

Max Activating Token Index: 913

Text #15

Max Range: 0.3985. Min Range: -0.3985

Max Act: 0.3034. Min Act: -0.0000

Data Index: 776903 (The Pile)

Max Activating Token Index: 192

Text #16

Max Range: 0.3985. Min Range: -0.3985

Max Act: 0.2957. Min Act: -0.0000

Data Index: 1534490 (The Pile)

Max Activating Token Index: 486

Text #17

Max Range: 0.3985. Min Range: -0.3985

Max Act: 0.3012. Min Act: -0.0000

Data Index: 1398733 (The Pile)

Max Activating Token Index: 314

Text #18

Max Range: 0.3985. Min Range: -0.3985

Max Act: 0.2910. Min Act: -0.0000

Data Index: 1976283 (The Pile)

Max Activating Token Index: 863

Text #19

Max Range: 0.3985. Min Range: -0.3985

Max Act: 0.2892. Min Act: -0.0000

Data Index: 629105 (The Pile)

Max Activating Token Index: 374