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

Dataset: The Pile

Neuron 817 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.8337. Min Act: -0.0000

Data Index: 153585 (The Pile)

Max Activating Token Index: 645

Text #1

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.8163. Min Act: -0.0000

Data Index: 1869323 (The Pile)

Max Activating Token Index: 192

Text #2

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.8346. Min Act: -0.0000

Data Index: 814890 (The Pile)

Max Activating Token Index: 502

Text #3

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.7986. Min Act: -0.0000

Data Index: 476597 (The Pile)

Max Activating Token Index: 175

Text #4

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.7755. Min Act: -0.0000

Data Index: 953094 (The Pile)

Max Activating Token Index: 887

Text #5

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.7480. Min Act: -0.0000

Data Index: 1107072 (The Pile)

Max Activating Token Index: 939

Text #6

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.7951. Min Act: -0.0000

Data Index: 1789894 (The Pile)

Max Activating Token Index: 489

Text #7

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.7418. Min Act: -0.0000

Data Index: 596551 (The Pile)

Max Activating Token Index: 645

Text #8

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.7888. Min Act: -0.0000

Data Index: 801221 (The Pile)

Max Activating Token Index: 983

Text #9

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.7590. Min Act: -0.0000

Data Index: 1878795 (The Pile)

Max Activating Token Index: 18

Text #10

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.7829. Min Act: -0.0000

Data Index: 1738647 (The Pile)

Max Activating Token Index: 211

Text #11

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.7297. Min Act: -0.0000

Data Index: 1702992 (The Pile)

Max Activating Token Index: 336

Text #12

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.7458. Min Act: -0.0000

Data Index: 1271428 (The Pile)

Max Activating Token Index: 623

Text #13

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.7450. Min Act: 0.0000

Data Index: 1573706 (The Pile)

Max Activating Token Index: 150

Text #14

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.7058. Min Act: -0.0000

Data Index: 1727279 (The Pile)

Max Activating Token Index: 87

Text #15

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.7185. Min Act: -0.0000

Data Index: 1123062 (The Pile)

Max Activating Token Index: 929

Text #16

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.6311. Min Act: -0.0000

Data Index: 145394 (The Pile)

Max Activating Token Index: 731

Text #17

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.7182. Min Act: -0.0000

Data Index: 1669781 (The Pile)

Max Activating Token Index: 530

Text #18

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.6616. Min Act: -0.0000

Data Index: 765276 (The Pile)

Max Activating Token Index: 997

Text #19

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.7574. Min Act: -0.0000

Data Index: 650325 (The Pile)

Max Activating Token Index: 904