Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3597 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.4934. Min Act: -0.0000

Data Index: 884591 (C4 (Web Text))

Max Activating Token Index: 499

Text #1

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.5110. Min Act: -0.0000

Data Index: 1239685 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.4189. Min Act: -0.0000

Data Index: 1167512 (C4 (Web Text))

Max Activating Token Index: 962

Text #3

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.3488. Min Act: -0.0000

Data Index: 1143558 (C4 (Web Text))

Max Activating Token Index: 148

Text #4

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.3936. Min Act: -0.0000

Data Index: 199855 (C4 (Web Text))

Max Activating Token Index: 513

Text #5

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.3444. Min Act: -0.0000

Data Index: 326940 (C4 (Web Text))

Max Activating Token Index: 888

Text #6

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.3389. Min Act: -0.0000

Data Index: 967220 (C4 (Web Text))

Max Activating Token Index: 516

Text #7

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.2957. Min Act: -0.0000

Data Index: 1129935 (C4 (Web Text))

Max Activating Token Index: 300

Text #8

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.3072. Min Act: -0.0000

Data Index: 1284810 (C4 (Web Text))

Max Activating Token Index: 495

Text #9

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.3066. Min Act: -0.0000

Data Index: 1034634 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.3174. Min Act: -0.0000

Data Index: 862913 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.3049. Min Act: -0.0000

Data Index: 1069303 (C4 (Web Text))

Max Activating Token Index: 522

Text #12

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.3097. Min Act: -0.0000

Data Index: 797767 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.3056. Min Act: -0.0000

Data Index: 155545 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.2775. Min Act: -0.0000

Data Index: 303208 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.2997. Min Act: -0.0000

Data Index: 111700 (C4 (Web Text))

Max Activating Token Index: 911

Text #16

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.2817. Min Act: -0.0000

Data Index: 1266008 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.2883. Min Act: -0.0000

Data Index: 1305233 (C4 (Web Text))

Max Activating Token Index: 494

Text #18

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.2775. Min Act: -0.0000

Data Index: 953450 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.2771. Min Act: -0.0000

Data Index: 312868 (C4 (Web Text))

Max Activating Token Index: 617