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

Dataset: The Pile

Neuron 3940 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: 1.1794. Min Range: -1.1794

Max Act: 1.1627. Min Act: -0.0000

Data Index: 85746 (The Pile)

Max Activating Token Index: 796

Text #1

Max Range: 1.1794. Min Range: -1.1794

Max Act: 1.1276. Min Act: -0.0000

Data Index: 1592579 (The Pile)

Max Activating Token Index: 399

Text #2

Max Range: 1.1794. Min Range: -1.1794

Max Act: 1.1794. Min Act: -0.0000

Data Index: 1612763 (The Pile)

Max Activating Token Index: 60

Text #3

Max Range: 1.1794. Min Range: -1.1794

Max Act: 1.1273. Min Act: -0.0000

Data Index: 1841980 (The Pile)

Max Activating Token Index: 502

Text #4

Max Range: 1.1794. Min Range: -1.1794

Max Act: 1.1319. Min Act: -0.0000

Data Index: 538189 (The Pile)

Max Activating Token Index: 292

Text #5

Max Range: 1.1794. Min Range: -1.1794

Max Act: 1.0792. Min Act: -0.0000

Data Index: 293870 (The Pile)

Max Activating Token Index: 358

Text #6

Max Range: 1.1794. Min Range: -1.1794

Max Act: 1.0602. Min Act: -0.0000

Data Index: 1348017 (The Pile)

Max Activating Token Index: 306

Text #7

Max Range: 1.1794. Min Range: -1.1794

Max Act: 1.0763. Min Act: -0.0000

Data Index: 1029741 (The Pile)

Max Activating Token Index: 136

Text #8

Max Range: 1.1794. Min Range: -1.1794

Max Act: 1.0139. Min Act: -0.0000

Data Index: 1355773 (The Pile)

Max Activating Token Index: 705

Text #9

Max Range: 1.1794. Min Range: -1.1794

Max Act: 1.0624. Min Act: -0.0000

Data Index: 1413670 (The Pile)

Max Activating Token Index: 993

Text #10

Max Range: 1.1794. Min Range: -1.1794

Max Act: 0.9549. Min Act: -0.0000

Data Index: 1468780 (The Pile)

Max Activating Token Index: 560

Text #11

Max Range: 1.1794. Min Range: -1.1794

Max Act: 0.9403. Min Act: -0.0000

Data Index: 247563 (The Pile)

Max Activating Token Index: 209

Text #12

Max Range: 1.1794. Min Range: -1.1794

Max Act: 0.9733. Min Act: -0.0000

Data Index: 1656670 (The Pile)

Max Activating Token Index: 155

Text #13

Max Range: 1.1794. Min Range: -1.1794

Max Act: 1.0194. Min Act: -0.0000

Data Index: 1922082 (The Pile)

Max Activating Token Index: 40

Text #14

Max Range: 1.1794. Min Range: -1.1794

Max Act: 0.9119. Min Act: -0.0000

Data Index: 1526864 (The Pile)

Max Activating Token Index: 382

Text #15

Max Range: 1.1794. Min Range: -1.1794

Max Act: 0.9939. Min Act: -0.0000

Data Index: 1708100 (The Pile)

Max Activating Token Index: 440

Text #16

Max Range: 1.1794. Min Range: -1.1794

Max Act: 0.8881. Min Act: -0.0000

Data Index: 1002495 (The Pile)

Max Activating Token Index: 985

Text #17

Max Range: 1.1794. Min Range: -1.1794

Max Act: 0.9761. Min Act: -0.0000

Data Index: 1350489 (The Pile)

Max Activating Token Index: 722

Text #18

Max Range: 1.1794. Min Range: -1.1794

Max Act: 0.9213. Min Act: -0.0000

Data Index: 848590 (The Pile)

Max Activating Token Index: 764

Text #19

Max Range: 1.1794. Min Range: -1.1794

Max Act: 0.9231. Min Act: -0.0000

Data Index: 704220 (The Pile)

Max Activating Token Index: 279