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

Dataset: The Pile

Neuron 1464 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: 3.2415. Min Range: -3.2415

Max Act: 3.1664. Min Act: -0.0000

Data Index: 543982 (The Pile)

Max Activating Token Index: 471

Text #1

Max Range: 3.2415. Min Range: -3.2415

Max Act: 3.1176. Min Act: -0.0000

Data Index: 1968574 (The Pile)

Max Activating Token Index: 264

Text #2

Max Range: 3.2415. Min Range: -3.2415

Max Act: 3.2415. Min Act: -0.0000

Data Index: 1289774 (The Pile)

Max Activating Token Index: 397

Text #3

Max Range: 3.2415. Min Range: -3.2415

Max Act: 2.9023. Min Act: -0.0000

Data Index: 457285 (The Pile)

Max Activating Token Index: 89

Text #4

Max Range: 3.2415. Min Range: -3.2415

Max Act: 3.0024. Min Act: -0.0000

Data Index: 290445 (The Pile)

Max Activating Token Index: 254

Text #5

Max Range: 3.2415. Min Range: -3.2415

Max Act: 2.5875. Min Act: -0.0000

Data Index: 541105 (The Pile)

Max Activating Token Index: 516

Text #6

Max Range: 3.2415. Min Range: -3.2415

Max Act: 2.5495. Min Act: -0.0000

Data Index: 998572 (The Pile)

Max Activating Token Index: 381

Text #7

Max Range: 3.2415. Min Range: -3.2415

Max Act: 2.8690. Min Act: -0.0000

Data Index: 296468 (The Pile)

Max Activating Token Index: 962

Text #8

Max Range: 3.2415. Min Range: -3.2415

Max Act: 2.9838. Min Act: -0.0000

Data Index: 657935 (The Pile)

Max Activating Token Index: 497

Text #9

Max Range: 3.2415. Min Range: -3.2415

Max Act: 2.6338. Min Act: -0.0000

Data Index: 1956467 (The Pile)

Max Activating Token Index: 337

Text #10

Max Range: 3.2415. Min Range: -3.2415

Max Act: 2.6309. Min Act: -0.0000

Data Index: 1990939 (The Pile)

Max Activating Token Index: 709

Text #11

Max Range: 3.2415. Min Range: -3.2415

Max Act: 2.6134. Min Act: -0.0000

Data Index: 194840 (The Pile)

Max Activating Token Index: 896

Text #12

Max Range: 3.2415. Min Range: -3.2415

Max Act: 2.5727. Min Act: -0.0000

Data Index: 243364 (The Pile)

Max Activating Token Index: 89

Text #13

Max Range: 3.2415. Min Range: -3.2415

Max Act: 2.6925. Min Act: -0.0000

Data Index: 949308 (The Pile)

Max Activating Token Index: 30

Text #14

Max Range: 3.2415. Min Range: -3.2415

Max Act: 2.5453. Min Act: -0.0000

Data Index: 160620 (The Pile)

Max Activating Token Index: 116

Text #15

Max Range: 3.2415. Min Range: -3.2415

Max Act: 2.3930. Min Act: -0.0000

Data Index: 175357 (The Pile)

Max Activating Token Index: 748

Text #16

Max Range: 3.2415. Min Range: -3.2415

Max Act: 2.2612. Min Act: -0.0000

Data Index: 512489 (The Pile)

Max Activating Token Index: 525

Text #17

Max Range: 3.2415. Min Range: -3.2415

Max Act: 2.6147. Min Act: -0.0000

Data Index: 1279197 (The Pile)

Max Activating Token Index: 518

Text #18

Max Range: 3.2415. Min Range: -3.2415

Max Act: 2.6123. Min Act: -0.0000

Data Index: 1698795 (The Pile)

Max Activating Token Index: 26

Text #19

Max Range: 3.2415. Min Range: -3.2415

Max Act: 2.1917. Min Act: -0.0000

Data Index: 900129 (The Pile)

Max Activating Token Index: 667