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

Dataset: The Pile

Neuron 1858 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.7918. Min Act: -0.0000

Data Index: 433293 (The Pile)

Max Activating Token Index: 809

Text #1

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.7236. Min Act: -0.0000

Data Index: 903914 (The Pile)

Max Activating Token Index: 833

Text #2

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.4891. Min Act: -0.0000

Data Index: 1841363 (The Pile)

Max Activating Token Index: 638

Text #3

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.4451. Min Act: -0.0000

Data Index: 1637064 (The Pile)

Max Activating Token Index: 1016

Text #4

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.3647. Min Act: -0.0000

Data Index: 690128 (The Pile)

Max Activating Token Index: 558

Text #5

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.3753. Min Act: -0.0000

Data Index: 653522 (The Pile)

Max Activating Token Index: 707

Text #6

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.4141. Min Act: -0.0000

Data Index: 1041374 (The Pile)

Max Activating Token Index: 893

Text #7

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.4405. Min Act: -0.0000

Data Index: 1263464 (The Pile)

Max Activating Token Index: 696

Text #8

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.4542. Min Act: -0.0000

Data Index: 1464005 (The Pile)

Max Activating Token Index: 558

Text #9

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.3570. Min Act: -0.0000

Data Index: 1067650 (The Pile)

Max Activating Token Index: 488

Text #10

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.3915. Min Act: -0.0000

Data Index: 836275 (The Pile)

Max Activating Token Index: 487

Text #11

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.3353. Min Act: -0.0000

Data Index: 272427 (The Pile)

Max Activating Token Index: 286

Text #12

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.3185. Min Act: -0.0000

Data Index: 447164 (The Pile)

Max Activating Token Index: 852

Text #13

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.3239. Min Act: -0.0000

Data Index: 1977107 (The Pile)

Max Activating Token Index: 300

Text #14

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.2297. Min Act: -0.0000

Data Index: 518868 (The Pile)

Max Activating Token Index: 551

Text #15

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.2400. Min Act: -0.0000

Data Index: 502708 (The Pile)

Max Activating Token Index: 390

Text #16

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.1056. Min Act: -0.0000

Data Index: 277193 (The Pile)

Max Activating Token Index: 810

Text #17

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.1678. Min Act: -0.0000

Data Index: 898949 (The Pile)

Max Activating Token Index: 408

Text #18

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.1957. Min Act: -0.0000

Data Index: 996702 (The Pile)

Max Activating Token Index: 902

Text #19

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.1078. Min Act: -0.0000

Data Index: 626648 (The Pile)

Max Activating Token Index: 686