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

Dataset: The Pile

Neuron 3607 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: 0.4683. Min Range: -0.4683

Max Act: 0.4683. Min Act: -0.0000

Data Index: 1853490 (The Pile)

Max Activating Token Index: 36

Text #1

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.4460. Min Act: -0.0000

Data Index: 1497091 (The Pile)

Max Activating Token Index: 110

Text #2

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.4604. Min Act: -0.0000

Data Index: 873270 (The Pile)

Max Activating Token Index: 944

Text #3

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3835. Min Act: 0.0000

Data Index: 1513214 (The Pile)

Max Activating Token Index: 243

Text #4

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3824. Min Act: -0.0000

Data Index: 1354023 (The Pile)

Max Activating Token Index: 1000

Text #5

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3683. Min Act: 0.0000

Data Index: 1990907 (The Pile)

Max Activating Token Index: 1009

Text #6

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3401. Min Act: -0.0000

Data Index: 1328045 (The Pile)

Max Activating Token Index: 239

Text #7

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3043. Min Act: -0.0000

Data Index: 1785500 (The Pile)

Max Activating Token Index: 826

Text #8

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3413. Min Act: -0.0000

Data Index: 472304 (The Pile)

Max Activating Token Index: 542

Text #9

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3348. Min Act: -0.0000

Data Index: 91795 (The Pile)

Max Activating Token Index: 414

Text #10

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3516. Min Act: -0.0000

Data Index: 695153 (The Pile)

Max Activating Token Index: 458

Text #11

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3209. Min Act: -0.0000

Data Index: 1945387 (The Pile)

Max Activating Token Index: 687

Text #12

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3343. Min Act: -0.0000

Data Index: 240511 (The Pile)

Max Activating Token Index: 348

Text #13

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3164. Min Act: 0.0000

Data Index: 1355031 (The Pile)

Max Activating Token Index: 817

Text #14

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3260. Min Act: -0.0000

Data Index: 1921192 (The Pile)

Max Activating Token Index: 369

Text #15

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3209. Min Act: -0.0000

Data Index: 223545 (The Pile)

Max Activating Token Index: 248

Text #16

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3198. Min Act: -0.0000

Data Index: 173480 (The Pile)

Max Activating Token Index: 950

Text #17

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.2991. Min Act: -0.0000

Data Index: 1634893 (The Pile)

Max Activating Token Index: 81

Text #18

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3152. Min Act: -0.0000

Data Index: 374178 (The Pile)

Max Activating Token Index: 573

Text #19

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3038. Min Act: -0.0000

Data Index: 997122 (The Pile)

Max Activating Token Index: 52