Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1054 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0998. Min Act: -0.0002

Data Index: 208324 (C4 (Web Text))

Max Activating Token Index: 341

Text #1

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.1038. Min Act: -0.0002

Data Index: 889893 (C4 (Web Text))

Max Activating Token Index: 664

Text #2

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.1031. Min Act: -0.0002

Data Index: 159551 (C4 (Web Text))

Max Activating Token Index: 340

Text #3

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0991. Min Act: -0.0002

Data Index: 74493 (C4 (Web Text))

Max Activating Token Index: 529

Text #4

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0995. Min Act: -0.0002

Data Index: 16961 (C4 (Web Text))

Max Activating Token Index: 930

Text #5

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0975. Min Act: -0.0002

Data Index: 1192339 (C4 (Web Text))

Max Activating Token Index: 480

Text #6

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0949. Min Act: -0.0002

Data Index: 12620 (C4 (Web Text))

Max Activating Token Index: 812

Text #7

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0953. Min Act: -0.0002

Data Index: 460282 (C4 (Web Text))

Max Activating Token Index: 372

Text #8

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0966. Min Act: -0.0002

Data Index: 888610 (C4 (Web Text))

Max Activating Token Index: 823

Text #9

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0974. Min Act: -0.0002

Data Index: 653169 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0947. Min Act: -0.0002

Data Index: 562360 (C4 (Web Text))

Max Activating Token Index: 634

Text #11

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0956. Min Act: -0.0002

Data Index: 765705 (C4 (Web Text))

Max Activating Token Index: 686

Text #12

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0916. Min Act: -0.0002

Data Index: 252817 (C4 (Web Text))

Max Activating Token Index: 786

Text #13

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0952. Min Act: -0.0002

Data Index: 1258842 (C4 (Web Text))

Max Activating Token Index: 826

Text #14

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0944. Min Act: -0.0002

Data Index: 682551 (C4 (Web Text))

Max Activating Token Index: 542

Text #15

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0926. Min Act: -0.0002

Data Index: 1158157 (C4 (Web Text))

Max Activating Token Index: 456

Text #16

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0945. Min Act: -0.0002

Data Index: 694530 (C4 (Web Text))

Max Activating Token Index: 906

Text #17

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0966. Min Act: -0.0002

Data Index: 1223869 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0938. Min Act: -0.0002

Data Index: 1173426 (C4 (Web Text))

Max Activating Token Index: 890

Text #19

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0945. Min Act: -0.0002

Data Index: 387386 (C4 (Web Text))

Max Activating Token Index: 656