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

Dataset: The Pile

Neuron 2946 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: 1.6421. Min Range: -1.6421

Max Act: 1.6421. Min Act: -0.0000

Data Index: 591626 (The Pile)

Max Activating Token Index: 772

Text #1

Max Range: 1.6421. Min Range: -1.6421

Max Act: 1.6302. Min Act: -0.0000

Data Index: 672671 (The Pile)

Max Activating Token Index: 703

Text #2

Max Range: 1.6421. Min Range: -1.6421

Max Act: 1.5069. Min Act: -0.0000

Data Index: 1359829 (The Pile)

Max Activating Token Index: 551

Text #3

Max Range: 1.6421. Min Range: -1.6421

Max Act: 1.5000. Min Act: -0.0000

Data Index: 1535225 (The Pile)

Max Activating Token Index: 104

Text #4

Max Range: 1.6421. Min Range: -1.6421

Max Act: 1.2998. Min Act: -0.0000

Data Index: 792549 (The Pile)

Max Activating Token Index: 139

Text #5

Max Range: 1.6421. Min Range: -1.6421

Max Act: 1.3601. Min Act: -0.0000

Data Index: 1532040 (The Pile)

Max Activating Token Index: 771

Text #6

Max Range: 1.6421. Min Range: -1.6421

Max Act: 1.4065. Min Act: -0.0000

Data Index: 880653 (The Pile)

Max Activating Token Index: 472

Text #7

Max Range: 1.6421. Min Range: -1.6421

Max Act: 1.2659. Min Act: -0.0000

Data Index: 23416 (The Pile)

Max Activating Token Index: 566

Text #8

Max Range: 1.6421. Min Range: -1.6421

Max Act: 1.2960. Min Act: -0.0000

Data Index: 545242 (The Pile)

Max Activating Token Index: 263

Text #9

Max Range: 1.6421. Min Range: -1.6421

Max Act: 1.2954. Min Act: -0.0000

Data Index: 324178 (The Pile)

Max Activating Token Index: 854

Text #10

Max Range: 1.6421. Min Range: -1.6421

Max Act: 1.2333. Min Act: -0.0000

Data Index: 1918709 (The Pile)

Max Activating Token Index: 976

Text #11

Max Range: 1.6421. Min Range: -1.6421

Max Act: 1.2028. Min Act: -0.0000

Data Index: 1784380 (The Pile)

Max Activating Token Index: 883

Text #12

Max Range: 1.6421. Min Range: -1.6421

Max Act: 1.2948. Min Act: -0.0000

Data Index: 1314866 (The Pile)

Max Activating Token Index: 221

Text #13

Max Range: 1.6421. Min Range: -1.6421

Max Act: 1.2082. Min Act: -0.0000

Data Index: 1022711 (The Pile)

Max Activating Token Index: 9

Text #14

Max Range: 1.6421. Min Range: -1.6421

Max Act: 1.1596. Min Act: -0.0000

Data Index: 1768362 (The Pile)

Max Activating Token Index: 70

Text #15

Max Range: 1.6421. Min Range: -1.6421

Max Act: 1.2373. Min Act: -0.0000

Data Index: 319220 (The Pile)

Max Activating Token Index: 988

Text #16

Max Range: 1.6421. Min Range: -1.6421

Max Act: 1.2169. Min Act: -0.0000

Data Index: 1866815 (The Pile)

Max Activating Token Index: 271

Text #17

Max Range: 1.6421. Min Range: -1.6421

Max Act: 1.1471. Min Act: -0.0000

Data Index: 343341 (The Pile)

Max Activating Token Index: 358

Text #18

Max Range: 1.6421. Min Range: -1.6421

Max Act: 1.1640. Min Act: -0.0000

Data Index: 624722 (The Pile)

Max Activating Token Index: 839

Text #19

Max Range: 1.6421. Min Range: -1.6421

Max Act: 1.1220. Min Act: -0.0000

Data Index: 585953 (The Pile)

Max Activating Token Index: 437