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

Dataset: The Pile

Neuron 1290 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.7980. Min Act: -0.0000

Data Index: 93596 (The Pile)

Max Activating Token Index: 259

Text #1

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.7806. Min Act: -0.0000

Data Index: 1018661 (The Pile)

Max Activating Token Index: 467

Text #2

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.6932. Min Act: -0.0000

Data Index: 261000 (The Pile)

Max Activating Token Index: 367

Text #3

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.7433. Min Act: -0.0000

Data Index: 1225886 (The Pile)

Max Activating Token Index: 842

Text #4

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.6477. Min Act: -0.0000

Data Index: 1322630 (The Pile)

Max Activating Token Index: 893

Text #5

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.6285. Min Act: -0.0000

Data Index: 1968882 (The Pile)

Max Activating Token Index: 705

Text #6

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.6475. Min Act: -0.0000

Data Index: 965423 (The Pile)

Max Activating Token Index: 735

Text #7

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.6193. Min Act: -0.0000

Data Index: 1846887 (The Pile)

Max Activating Token Index: 773

Text #8

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.6496. Min Act: -0.0000

Data Index: 1358928 (The Pile)

Max Activating Token Index: 251

Text #9

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.5999. Min Act: -0.0000

Data Index: 1787879 (The Pile)

Max Activating Token Index: 593

Text #10

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.6122. Min Act: -0.0000

Data Index: 773274 (The Pile)

Max Activating Token Index: 721

Text #11

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.6291. Min Act: -0.0000

Data Index: 1744159 (The Pile)

Max Activating Token Index: 717

Text #12

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.6019. Min Act: -0.0000

Data Index: 597943 (The Pile)

Max Activating Token Index: 416

Text #13

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.5357. Min Act: -0.0000

Data Index: 1632129 (The Pile)

Max Activating Token Index: 550

Text #14

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.5464. Min Act: -0.0000

Data Index: 1231442 (The Pile)

Max Activating Token Index: 573

Text #15

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.5592. Min Act: -0.0000

Data Index: 1926608 (The Pile)

Max Activating Token Index: 657

Text #16

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.5577. Min Act: -0.0000

Data Index: 277269 (The Pile)

Max Activating Token Index: 834

Text #17

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.5629. Min Act: -0.0000

Data Index: 830202 (The Pile)

Max Activating Token Index: 669

Text #18

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.5464. Min Act: -0.0000

Data Index: 252801 (The Pile)

Max Activating Token Index: 370

Text #19

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.5780. Min Act: -0.0000

Data Index: 1339905 (The Pile)

Max Activating Token Index: 1003