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

Dataset: The Pile

Neuron 45 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: 1.2687. Min Range: -1.2687

Max Act: 1.2687. Min Act: -0.0000

Data Index: 1242384 (The Pile)

Max Activating Token Index: 397

Text #1

Max Range: 1.2687. Min Range: -1.2687

Max Act: 1.2527. Min Act: -0.0000

Data Index: 1158345 (The Pile)

Max Activating Token Index: 148

Text #2

Max Range: 1.2687. Min Range: -1.2687

Max Act: 1.2025. Min Act: -0.0000

Data Index: 1404395 (The Pile)

Max Activating Token Index: 680

Text #3

Max Range: 1.2687. Min Range: -1.2687

Max Act: 1.1186. Min Act: -0.0000

Data Index: 1343273 (The Pile)

Max Activating Token Index: 351

Text #4

Max Range: 1.2687. Min Range: -1.2687

Max Act: 1.1723. Min Act: -0.0000

Data Index: 165782 (The Pile)

Max Activating Token Index: 415

Text #5

Max Range: 1.2687. Min Range: -1.2687

Max Act: 1.1201. Min Act: -0.0000

Data Index: 1026797 (The Pile)

Max Activating Token Index: 260

Text #6

Max Range: 1.2687. Min Range: -1.2687

Max Act: 1.0552. Min Act: -0.0000

Data Index: 1104933 (The Pile)

Max Activating Token Index: 227

Text #7

Max Range: 1.2687. Min Range: -1.2687

Max Act: 1.1339. Min Act: -0.0000

Data Index: 394352 (The Pile)

Max Activating Token Index: 57

Text #8

Max Range: 1.2687. Min Range: -1.2687

Max Act: 1.0242. Min Act: -0.0000

Data Index: 1124436 (The Pile)

Max Activating Token Index: 260

Text #9

Max Range: 1.2687. Min Range: -1.2687

Max Act: 1.0927. Min Act: -0.0000

Data Index: 141873 (The Pile)

Max Activating Token Index: 116

Text #10

Max Range: 1.2687. Min Range: -1.2687

Max Act: 1.0062. Min Act: -0.0000

Data Index: 207720 (The Pile)

Max Activating Token Index: 884

Text #11

Max Range: 1.2687. Min Range: -1.2687

Max Act: 0.9047. Min Act: -0.0000

Data Index: 1783632 (The Pile)

Max Activating Token Index: 994

Text #12

Max Range: 1.2687. Min Range: -1.2687

Max Act: 1.0315. Min Act: -0.0000

Data Index: 1059663 (The Pile)

Max Activating Token Index: 825

Text #13

Max Range: 1.2687. Min Range: -1.2687

Max Act: 0.9737. Min Act: -0.0000

Data Index: 594768 (The Pile)

Max Activating Token Index: 785

Text #14

Max Range: 1.2687. Min Range: -1.2687

Max Act: 0.9513. Min Act: -0.0000

Data Index: 791949 (The Pile)

Max Activating Token Index: 951

Text #15

Max Range: 1.2687. Min Range: -1.2687

Max Act: 0.9749. Min Act: -0.0000

Data Index: 1412519 (The Pile)

Max Activating Token Index: 680

Text #16

Max Range: 1.2687. Min Range: -1.2687

Max Act: 0.8755. Min Act: -0.0000

Data Index: 894081 (The Pile)

Max Activating Token Index: 830

Text #17

Max Range: 1.2687. Min Range: -1.2687

Max Act: 0.8903. Min Act: -0.0001

Data Index: 1349044 (The Pile)

Max Activating Token Index: 880

Text #18

Max Range: 1.2687. Min Range: -1.2687

Max Act: 0.7881. Min Act: -0.0000

Data Index: 685900 (The Pile)

Max Activating Token Index: 743

Text #19

Max Range: 1.2687. Min Range: -1.2687

Max Act: 0.9603. Min Act: -0.0000

Data Index: 1258340 (The Pile)

Max Activating Token Index: 640