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

Dataset: The Pile

Neuron 2882 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: 0.4594. Min Range: -0.4594

Max Act: 0.4594. Min Act: -0.0000

Data Index: 1679075 (The Pile)

Max Activating Token Index: 378

Text #1

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.4173. Min Act: -0.0000

Data Index: 1286160 (The Pile)

Max Activating Token Index: 934

Text #2

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.4359. Min Act: -0.0000

Data Index: 926973 (The Pile)

Max Activating Token Index: 295

Text #3

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.4362. Min Act: -0.0000

Data Index: 1495834 (The Pile)

Max Activating Token Index: 740

Text #4

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.4326. Min Act: -0.0000

Data Index: 173199 (The Pile)

Max Activating Token Index: 264

Text #5

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.4180. Min Act: -0.0000

Data Index: 479228 (The Pile)

Max Activating Token Index: 443

Text #6

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.4069. Min Act: -0.0000

Data Index: 1006028 (The Pile)

Max Activating Token Index: 209

Text #7

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.4147. Min Act: -0.0000

Data Index: 158906 (The Pile)

Max Activating Token Index: 297

Text #8

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3905. Min Act: -0.0000

Data Index: 112718 (The Pile)

Max Activating Token Index: 620

Text #9

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.4012. Min Act: -0.0000

Data Index: 1521697 (The Pile)

Max Activating Token Index: 106

Text #10

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3979. Min Act: -0.0000

Data Index: 1517212 (The Pile)

Max Activating Token Index: 395

Text #11

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.4039. Min Act: -0.0000

Data Index: 1263451 (The Pile)

Max Activating Token Index: 1018

Text #12

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3828. Min Act: -0.0000

Data Index: 1855852 (The Pile)

Max Activating Token Index: 621

Text #13

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3956. Min Act: -0.0000

Data Index: 790246 (The Pile)

Max Activating Token Index: 500

Text #14

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3882. Min Act: -0.0000

Data Index: 124928 (The Pile)

Max Activating Token Index: 116

Text #15

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3830. Min Act: -0.0000

Data Index: 1763264 (The Pile)

Max Activating Token Index: 714

Text #16

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3827. Min Act: -0.0000

Data Index: 737567 (The Pile)

Max Activating Token Index: 212

Text #17

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3823. Min Act: -0.0000

Data Index: 1830878 (The Pile)

Max Activating Token Index: 287

Text #18

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3697. Min Act: -0.0000

Data Index: 906407 (The Pile)

Max Activating Token Index: 375

Text #19

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3914. Min Act: -0.0000

Data Index: 487389 (The Pile)

Max Activating Token Index: 863