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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1721 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4062. Min Range: -0.4062

Max Act: 0.3634. Min Act: -0.0000

Data Index: 371949 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 0.4062. Min Range: -0.4062

Max Act: 0.4062. Min Act: -0.0000

Data Index: 344665 (C4 (Web Text))

Max Activating Token Index: 723

Text #2

Max Range: 0.4062. Min Range: -0.4062

Max Act: 0.3463. Min Act: -0.0000

Data Index: 199543 (C4 (Web Text))

Max Activating Token Index: 746

Text #3

Max Range: 0.4062. Min Range: -0.4062

Max Act: 0.3328. Min Act: -0.0000

Data Index: 1280920 (C4 (Web Text))

Max Activating Token Index: 955

Text #4

Max Range: 0.4062. Min Range: -0.4062

Max Act: 0.3494. Min Act: -0.0000

Data Index: 198936 (C4 (Web Text))

Max Activating Token Index: 617

Text #5

Max Range: 0.4062. Min Range: -0.4062

Max Act: 0.3183. Min Act: -0.0000

Data Index: 1181773 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 0.4062. Min Range: -0.4062

Max Act: 0.3205. Min Act: -0.0000

Data Index: 481 (C4 (Web Text))

Max Activating Token Index: 225

Text #7

Max Range: 0.4062. Min Range: -0.4062

Max Act: 0.2943. Min Act: -0.0000

Data Index: 381463 (C4 (Web Text))

Max Activating Token Index: 1000

Text #8

Max Range: 0.4062. Min Range: -0.4062

Max Act: 0.3149. Min Act: -0.0000

Data Index: 419467 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 0.4062. Min Range: -0.4062

Max Act: 0.3066. Min Act: -0.0000

Data Index: 910098 (C4 (Web Text))

Max Activating Token Index: 734

Text #10

Max Range: 0.4062. Min Range: -0.4062

Max Act: 0.3097. Min Act: -0.0000

Data Index: 1263442 (C4 (Web Text))

Max Activating Token Index: 706

Text #11

Max Range: 0.4062. Min Range: -0.4062

Max Act: 0.2902. Min Act: -0.0000

Data Index: 1095523 (C4 (Web Text))

Max Activating Token Index: 343

Text #12

Max Range: 0.4062. Min Range: -0.4062

Max Act: 0.2720. Min Act: -0.0000

Data Index: 555025 (C4 (Web Text))

Max Activating Token Index: 58

Text #13

Max Range: 0.4062. Min Range: -0.4062

Max Act: 0.2845. Min Act: -0.0000

Data Index: 1308808 (C4 (Web Text))

Max Activating Token Index: 938

Text #14

Max Range: 0.4062. Min Range: -0.4062

Max Act: 0.2881. Min Act: -0.0000

Data Index: 364247 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 0.4062. Min Range: -0.4062

Max Act: 0.2759. Min Act: -0.0000

Data Index: 897635 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 0.4062. Min Range: -0.4062

Max Act: 0.2753. Min Act: -0.0000

Data Index: 1034281 (C4 (Web Text))

Max Activating Token Index: 478

Text #17

Max Range: 0.4062. Min Range: -0.4062

Max Act: 0.2706. Min Act: -0.0000

Data Index: 1243479 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 0.4062. Min Range: -0.4062

Max Act: 0.2738. Min Act: -0.0000

Data Index: 698139 (C4 (Web Text))

Max Activating Token Index: 711

Text #19

Max Range: 0.4062. Min Range: -0.4062

Max Act: 0.2757. Min Act: -0.0000

Data Index: 995838 (C4 (Web Text))

Max Activating Token Index: 915