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

Dataset: The Pile

Neuron 2190 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: 0.7805. Min Range: -0.7805

Max Act: 0.7805. Min Act: -0.0000

Data Index: 1089634 (The Pile)

Max Activating Token Index: 299

Text #1

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.7461. Min Act: -0.0000

Data Index: 586481 (The Pile)

Max Activating Token Index: 550

Text #2

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.7466. Min Act: -0.0000

Data Index: 572731 (The Pile)

Max Activating Token Index: 356

Text #3

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6681. Min Act: -0.0000

Data Index: 1677766 (The Pile)

Max Activating Token Index: 53

Text #4

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.7054. Min Act: -0.0000

Data Index: 1863273 (The Pile)

Max Activating Token Index: 519

Text #5

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.7171. Min Act: -0.0000

Data Index: 1260706 (The Pile)

Max Activating Token Index: 1013

Text #6

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6694. Min Act: -0.0000

Data Index: 301995 (The Pile)

Max Activating Token Index: 850

Text #7

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6519. Min Act: -0.0000

Data Index: 228358 (The Pile)

Max Activating Token Index: 507

Text #8

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6862. Min Act: -0.0000

Data Index: 684644 (The Pile)

Max Activating Token Index: 147

Text #9

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6801. Min Act: -0.0000

Data Index: 1483096 (The Pile)

Max Activating Token Index: 668

Text #10

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6193. Min Act: -0.0000

Data Index: 768972 (The Pile)

Max Activating Token Index: 615

Text #11

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6022. Min Act: -0.0000

Data Index: 1294735 (The Pile)

Max Activating Token Index: 1019

Text #12

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.5607. Min Act: -0.0000

Data Index: 376370 (The Pile)

Max Activating Token Index: 575

Text #13

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6437. Min Act: -0.0000

Data Index: 789228 (The Pile)

Max Activating Token Index: 993

Text #14

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.5639. Min Act: -0.0000

Data Index: 1174556 (The Pile)

Max Activating Token Index: 689

Text #15

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.5551. Min Act: -0.0000

Data Index: 522318 (The Pile)

Max Activating Token Index: 1011

Text #16

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.5897. Min Act: -0.0000

Data Index: 1824200 (The Pile)

Max Activating Token Index: 271

Text #17

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.5587. Min Act: -0.0000

Data Index: 500090 (The Pile)

Max Activating Token Index: 846

Text #18

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.5574. Min Act: -0.0000

Data Index: 1921461 (The Pile)

Max Activating Token Index: 332

Text #19

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.5570. Min Act: -0.0000

Data Index: 1269815 (The Pile)

Max Activating Token Index: 803