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

Dataset: The Pile

Neuron 951 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: 0.3878. Min Range: -0.3878

Max Act: 0.3878. Min Act: -0.0000

Data Index: 322726 (The Pile)

Max Activating Token Index: 789

Text #1

Max Range: 0.3878. Min Range: -0.3878

Max Act: 0.3603. Min Act: -0.0000

Data Index: 1985798 (The Pile)

Max Activating Token Index: 71

Text #2

Max Range: 0.3878. Min Range: -0.3878

Max Act: 0.3351. Min Act: -0.0000

Data Index: 1877795 (The Pile)

Max Activating Token Index: 989

Text #3

Max Range: 0.3878. Min Range: -0.3878

Max Act: 0.3354. Min Act: -0.0000

Data Index: 976373 (The Pile)

Max Activating Token Index: 695

Text #4

Max Range: 0.3878. Min Range: -0.3878

Max Act: 0.3315. Min Act: -0.0000

Data Index: 694175 (The Pile)

Max Activating Token Index: 842

Text #5

Max Range: 0.3878. Min Range: -0.3878

Max Act: 0.3402. Min Act: -0.0000

Data Index: 807464 (The Pile)

Max Activating Token Index: 130

Text #6

Max Range: 0.3878. Min Range: -0.3878

Max Act: 0.3136. Min Act: -0.0000

Data Index: 1430384 (The Pile)

Max Activating Token Index: 449

Text #7

Max Range: 0.3878. Min Range: -0.3878

Max Act: 0.3317. Min Act: -0.0000

Data Index: 1365661 (The Pile)

Max Activating Token Index: 564

Text #8

Max Range: 0.3878. Min Range: -0.3878

Max Act: 0.2943. Min Act: -0.0000

Data Index: 1046792 (The Pile)

Max Activating Token Index: 938

Text #9

Max Range: 0.3878. Min Range: -0.3878

Max Act: 0.3446. Min Act: -0.0000

Data Index: 133551 (The Pile)

Max Activating Token Index: 721

Text #10

Max Range: 0.3878. Min Range: -0.3878

Max Act: 0.3128. Min Act: -0.0000

Data Index: 1615317 (The Pile)

Max Activating Token Index: 872

Text #11

Max Range: 0.3878. Min Range: -0.3878

Max Act: 0.2984. Min Act: -0.0000

Data Index: 605506 (The Pile)

Max Activating Token Index: 333

Text #12

Max Range: 0.3878. Min Range: -0.3878

Max Act: 0.2866. Min Act: -0.0000

Data Index: 1536630 (The Pile)

Max Activating Token Index: 564

Text #13

Max Range: 0.3878. Min Range: -0.3878

Max Act: 0.2888. Min Act: -0.0000

Data Index: 195019 (The Pile)

Max Activating Token Index: 254

Text #14

Max Range: 0.3878. Min Range: -0.3878

Max Act: 0.3092. Min Act: 0.0000

Data Index: 582820 (The Pile)

Max Activating Token Index: 835

Text #15

Max Range: 0.3878. Min Range: -0.3878

Max Act: 0.2792. Min Act: -0.0000

Data Index: 965940 (The Pile)

Max Activating Token Index: 511

Text #16

Max Range: 0.3878. Min Range: -0.3878

Max Act: 0.2570. Min Act: -0.0000

Data Index: 1302302 (The Pile)

Max Activating Token Index: 812

Text #17

Max Range: 0.3878. Min Range: -0.3878

Max Act: 0.3090. Min Act: -0.0000

Data Index: 514446 (The Pile)

Max Activating Token Index: 692

Text #18

Max Range: 0.3878. Min Range: -0.3878

Max Act: 0.2700. Min Act: -0.0000

Data Index: 1430939 (The Pile)

Max Activating Token Index: 786

Text #19

Max Range: 0.3878. Min Range: -0.3878

Max Act: 0.2710. Min Act: -0.0000

Data Index: 1990605 (The Pile)

Max Activating Token Index: 636