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

Dataset: The Pile

Neuron 588 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1890. Min Range: -1.1890

Max Act: 1.1890. Min Act: -0.0000

Data Index: 123824 (The Pile)

Max Activating Token Index: 445

Text #1

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.9694. Min Act: -0.0000

Data Index: 1067114 (The Pile)

Max Activating Token Index: 42

Text #2

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.9474. Min Act: -0.0000

Data Index: 971896 (The Pile)

Max Activating Token Index: 997

Text #3

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.8347. Min Act: -0.0000

Data Index: 1272999 (The Pile)

Max Activating Token Index: 1007

Text #4

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.8664. Min Act: -0.0000

Data Index: 4199 (The Pile)

Max Activating Token Index: 1015

Text #5

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.9168. Min Act: -0.0000

Data Index: 548259 (The Pile)

Max Activating Token Index: 469

Text #6

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.8752. Min Act: -0.0000

Data Index: 1785413 (The Pile)

Max Activating Token Index: 522

Text #7

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.8376. Min Act: -0.0000

Data Index: 89427 (The Pile)

Max Activating Token Index: 919

Text #8

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.8739. Min Act: -0.0000

Data Index: 1747988 (The Pile)

Max Activating Token Index: 669

Text #9

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.9256. Min Act: -0.0000

Data Index: 1211036 (The Pile)

Max Activating Token Index: 328

Text #10

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.8163. Min Act: -0.0000

Data Index: 1137075 (The Pile)

Max Activating Token Index: 832

Text #11

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.8655. Min Act: -0.0000

Data Index: 1509394 (The Pile)

Max Activating Token Index: 912

Text #12

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.8944. Min Act: -0.0000

Data Index: 326117 (The Pile)

Max Activating Token Index: 87

Text #13

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.8442. Min Act: -0.0000

Data Index: 1688467 (The Pile)

Max Activating Token Index: 338

Text #14

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.7944. Min Act: -0.0000

Data Index: 1553871 (The Pile)

Max Activating Token Index: 651

Text #15

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.8176. Min Act: -0.0000

Data Index: 1970306 (The Pile)

Max Activating Token Index: 232

Text #16

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.8141. Min Act: -0.0000

Data Index: 1624916 (The Pile)

Max Activating Token Index: 618

Text #17

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.8956. Min Act: -0.0000

Data Index: 1198737 (The Pile)

Max Activating Token Index: 363

Text #18

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.8931. Min Act: -0.0000

Data Index: 1344482 (The Pile)

Max Activating Token Index: 852

Text #19

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.8660. Min Act: -0.0000

Data Index: 756337 (The Pile)

Max Activating Token Index: 212