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

Dataset: The Pile

Neuron 3209 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1398. Min Range: -1.1398

Max Act: 1.1271. Min Act: -0.0000

Data Index: 166871 (The Pile)

Max Activating Token Index: 1008

Text #1

Max Range: 1.1398. Min Range: -1.1398

Max Act: 1.1398. Min Act: -0.0000

Data Index: 232445 (The Pile)

Max Activating Token Index: 377

Text #2

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.9318. Min Act: -0.0000

Data Index: 1914662 (The Pile)

Max Activating Token Index: 413

Text #3

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.7882. Min Act: -0.0000

Data Index: 1148456 (The Pile)

Max Activating Token Index: 883

Text #4

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.7929. Min Act: -0.0000

Data Index: 235876 (The Pile)

Max Activating Token Index: 543

Text #5

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.7853. Min Act: -0.0000

Data Index: 1714027 (The Pile)

Max Activating Token Index: 397

Text #6

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.7522. Min Act: -0.0000

Data Index: 683116 (The Pile)

Max Activating Token Index: 913

Text #7

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.7352. Min Act: -0.0000

Data Index: 1403811 (The Pile)

Max Activating Token Index: 870

Text #8

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.7263. Min Act: -0.0000

Data Index: 1156997 (The Pile)

Max Activating Token Index: 934

Text #9

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.7468. Min Act: -0.0000

Data Index: 1033 (The Pile)

Max Activating Token Index: 953

Text #10

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.7147. Min Act: -0.0000

Data Index: 1217734 (The Pile)

Max Activating Token Index: 257

Text #11

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.7297. Min Act: -0.0000

Data Index: 468608 (The Pile)

Max Activating Token Index: 674

Text #12

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.7278. Min Act: -0.0000

Data Index: 901472 (The Pile)

Max Activating Token Index: 835

Text #13

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.6682. Min Act: 0.0000

Data Index: 591123 (The Pile)

Max Activating Token Index: 67

Text #14

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.6895. Min Act: -0.0000

Data Index: 156541 (The Pile)

Max Activating Token Index: 654

Text #15

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.6575. Min Act: -0.0000

Data Index: 1546718 (The Pile)

Max Activating Token Index: 499

Text #16

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.6771. Min Act: -0.0000

Data Index: 1012589 (The Pile)

Max Activating Token Index: 1002

Text #17

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.6459. Min Act: -0.0000

Data Index: 822275 (The Pile)

Max Activating Token Index: 81

Text #18

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.6910. Min Act: -0.0000

Data Index: 79072 (The Pile)

Max Activating Token Index: 582

Text #19

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.6394. Min Act: -0.0000

Data Index: 1702989 (The Pile)

Max Activating Token Index: 863