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

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

Neuron 1998 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: 0.4320. Min Range: -0.4320

Max Act: 0.4320. Min Act: -0.0000

Data Index: 747021 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 0.4320. Min Range: -0.4320

Max Act: 0.3838. Min Act: -0.0000

Data Index: 749360 (C4 (Web Text))

Max Activating Token Index: 722

Text #2

Max Range: 0.4320. Min Range: -0.4320

Max Act: 0.3550. Min Act: -0.0000

Data Index: 721868 (C4 (Web Text))

Max Activating Token Index: 118

Text #3

Max Range: 0.4320. Min Range: -0.4320

Max Act: 0.3469. Min Act: -0.0000

Data Index: 1291274 (C4 (Web Text))

Max Activating Token Index: 602

Text #4

Max Range: 0.4320. Min Range: -0.4320

Max Act: 0.3393. Min Act: -0.0000

Data Index: 330735 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 0.4320. Min Range: -0.4320

Max Act: 0.3193. Min Act: -0.0000

Data Index: 655936 (C4 (Web Text))

Max Activating Token Index: 533

Text #6

Max Range: 0.4320. Min Range: -0.4320

Max Act: 0.3168. Min Act: -0.0000

Data Index: 1165921 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 0.4320. Min Range: -0.4320

Max Act: 0.3032. Min Act: -0.0000

Data Index: 893661 (C4 (Web Text))

Max Activating Token Index: 724

Text #8

Max Range: 0.4320. Min Range: -0.4320

Max Act: 0.2899. Min Act: -0.0000

Data Index: 275116 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 0.4320. Min Range: -0.4320

Max Act: 0.2804. Min Act: -0.0000

Data Index: 177209 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 0.4320. Min Range: -0.4320

Max Act: 0.2888. Min Act: -0.0000

Data Index: 922232 (C4 (Web Text))

Max Activating Token Index: 405

Text #11

Max Range: 0.4320. Min Range: -0.4320

Max Act: 0.2847. Min Act: -0.0000

Data Index: 1060825 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 0.4320. Min Range: -0.4320

Max Act: 0.2769. Min Act: -0.0000

Data Index: 843148 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 0.4320. Min Range: -0.4320

Max Act: 0.2934. Min Act: -0.0000

Data Index: 904758 (C4 (Web Text))

Max Activating Token Index: 944

Text #14

Max Range: 0.4320. Min Range: -0.4320

Max Act: 0.2866. Min Act: -0.0000

Data Index: 254456 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 0.4320. Min Range: -0.4320

Max Act: 0.2844. Min Act: -0.0000

Data Index: 318828 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 0.4320. Min Range: -0.4320

Max Act: 0.2785. Min Act: -0.0000

Data Index: 977041 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 0.4320. Min Range: -0.4320

Max Act: 0.2637. Min Act: -0.0000

Data Index: 391017 (C4 (Web Text))

Max Activating Token Index: 831

Text #18

Max Range: 0.4320. Min Range: -0.4320

Max Act: 0.2708. Min Act: -0.0000

Data Index: 1261809 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 0.4320. Min Range: -0.4320

Max Act: 0.2785. Min Act: -0.0000

Data Index: 1239413 (C4 (Web Text))

Max Activating Token Index: 467