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

Dataset: The Pile

Neuron 3366 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.9367. Min Act: -0.0000

Data Index: 147823 (The Pile)

Max Activating Token Index: 365

Text #1

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.8742. Min Act: -0.0000

Data Index: 850585 (The Pile)

Max Activating Token Index: 275

Text #2

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.8218. Min Act: -0.0000

Data Index: 513887 (The Pile)

Max Activating Token Index: 594

Text #3

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.7956. Min Act: -0.0000

Data Index: 744356 (The Pile)

Max Activating Token Index: 447

Text #4

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.7355. Min Act: -0.0000

Data Index: 506398 (The Pile)

Max Activating Token Index: 417

Text #5

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.7676. Min Act: -0.0000

Data Index: 1544052 (The Pile)

Max Activating Token Index: 510

Text #6

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.7671. Min Act: -0.0000

Data Index: 603408 (The Pile)

Max Activating Token Index: 332

Text #7

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.7321. Min Act: -0.0000

Data Index: 1807681 (The Pile)

Max Activating Token Index: 600

Text #8

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.6811. Min Act: -0.0000

Data Index: 352213 (The Pile)

Max Activating Token Index: 728

Text #9

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.7017. Min Act: -0.0000

Data Index: 916899 (The Pile)

Max Activating Token Index: 657

Text #10

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.7673. Min Act: -0.0000

Data Index: 1849722 (The Pile)

Max Activating Token Index: 833

Text #11

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.7155. Min Act: -0.0000

Data Index: 697934 (The Pile)

Max Activating Token Index: 69

Text #12

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.7061. Min Act: -0.0000

Data Index: 93651 (The Pile)

Max Activating Token Index: 338

Text #13

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.7376. Min Act: -0.0000

Data Index: 1555253 (The Pile)

Max Activating Token Index: 262

Text #14

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.6975. Min Act: -0.0000

Data Index: 530971 (The Pile)

Max Activating Token Index: 210

Text #15

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.7336. Min Act: -0.0000

Data Index: 1950644 (The Pile)

Max Activating Token Index: 471

Text #16

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.6819. Min Act: -0.0000

Data Index: 1533987 (The Pile)

Max Activating Token Index: 413

Text #17

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.7241. Min Act: -0.0000

Data Index: 1874753 (The Pile)

Max Activating Token Index: 536

Text #18

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.6588. Min Act: -0.0000

Data Index: 1905089 (The Pile)

Max Activating Token Index: 233

Text #19

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.6644. Min Act: -0.0000

Data Index: 172378 (The Pile)

Max Activating Token Index: 131