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

Dataset: The Pile

Neuron 4508 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: 0.7209. Min Range: -0.7209

Max Act: 0.7209. Min Act: -0.0000

Data Index: 219804 (The Pile)

Max Activating Token Index: 44

Text #1

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.5962. Min Act: -0.0000

Data Index: 925667 (The Pile)

Max Activating Token Index: 722

Text #2

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.6187. Min Act: -0.0000

Data Index: 189342 (The Pile)

Max Activating Token Index: 805

Text #3

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.6584. Min Act: -0.0000

Data Index: 1829343 (The Pile)

Max Activating Token Index: 964

Text #4

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.6156. Min Act: -0.0000

Data Index: 1307707 (The Pile)

Max Activating Token Index: 5

Text #5

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.5554. Min Act: -0.0000

Data Index: 162025 (The Pile)

Max Activating Token Index: 645

Text #6

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.5777. Min Act: -0.0000

Data Index: 247105 (The Pile)

Max Activating Token Index: 15

Text #7

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.5744. Min Act: -0.0000

Data Index: 1987277 (The Pile)

Max Activating Token Index: 649

Text #8

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.5317. Min Act: -0.0000

Data Index: 43679 (The Pile)

Max Activating Token Index: 614

Text #9

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.5524. Min Act: -0.0000

Data Index: 1671879 (The Pile)

Max Activating Token Index: 865

Text #10

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.5792. Min Act: -0.0000

Data Index: 1687732 (The Pile)

Max Activating Token Index: 773

Text #11

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.5670. Min Act: -0.0000

Data Index: 467430 (The Pile)

Max Activating Token Index: 576

Text #12

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.5357. Min Act: -0.0000

Data Index: 849650 (The Pile)

Max Activating Token Index: 809

Text #13

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.5616. Min Act: -0.0000

Data Index: 836708 (The Pile)

Max Activating Token Index: 536

Text #14

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.5735. Min Act: -0.0000

Data Index: 1811446 (The Pile)

Max Activating Token Index: 842

Text #15

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.5345. Min Act: -0.0000

Data Index: 1688036 (The Pile)

Max Activating Token Index: 850

Text #16

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.5501. Min Act: -0.0000

Data Index: 1553318 (The Pile)

Max Activating Token Index: 17

Text #17

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.5319. Min Act: -0.0000

Data Index: 272388 (The Pile)

Max Activating Token Index: 442

Text #18

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.5639. Min Act: -0.0000

Data Index: 1938218 (The Pile)

Max Activating Token Index: 895

Text #19

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.5416. Min Act: -0.0000

Data Index: 1766096 (The Pile)

Max Activating Token Index: 288