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

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

Neuron 583 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.5722. Min Range: -7.5722

Max Act: 7.5722. Min Act: -0.0000

Data Index: 1044833 (C4 (Web Text))

Max Activating Token Index: 215

Text #1

Max Range: 7.5722. Min Range: -7.5722

Max Act: 6.8093. Min Act: -0.0000

Data Index: 447234 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 7.5722. Min Range: -7.5722

Max Act: 6.7358. Min Act: -0.0000

Data Index: 237345 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 7.5722. Min Range: -7.5722

Max Act: 6.3717. Min Act: -0.0000

Data Index: 79353 (C4 (Web Text))

Max Activating Token Index: 593

Text #4

Max Range: 7.5722. Min Range: -7.5722

Max Act: 6.2156. Min Act: -0.0000

Data Index: 1336071 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 7.5722. Min Range: -7.5722

Max Act: 6.2437. Min Act: -0.0000

Data Index: 919887 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 7.5722. Min Range: -7.5722

Max Act: 5.9447. Min Act: -0.0000

Data Index: 1020914 (C4 (Web Text))

Max Activating Token Index: 383

Text #7

Max Range: 7.5722. Min Range: -7.5722

Max Act: 5.8188. Min Act: -0.0000

Data Index: 1286496 (C4 (Web Text))

Max Activating Token Index: 535

Text #8

Max Range: 7.5722. Min Range: -7.5722

Max Act: 5.7029. Min Act: -0.0000

Data Index: 659850 (C4 (Web Text))

Max Activating Token Index: 508

Text #9

Max Range: 7.5722. Min Range: -7.5722

Max Act: 5.4912. Min Act: -0.0000

Data Index: 319539 (C4 (Web Text))

Max Activating Token Index: 594

Text #10

Max Range: 7.5722. Min Range: -7.5722

Max Act: 5.6475. Min Act: -0.0000

Data Index: 699917 (C4 (Web Text))

Max Activating Token Index: 832

Text #11

Max Range: 7.5722. Min Range: -7.5722

Max Act: 6.0295. Min Act: -0.0000

Data Index: 1319491 (C4 (Web Text))

Max Activating Token Index: 555

Text #12

Max Range: 7.5722. Min Range: -7.5722

Max Act: 5.4022. Min Act: -0.0000

Data Index: 185684 (C4 (Web Text))

Max Activating Token Index: 750

Text #13

Max Range: 7.5722. Min Range: -7.5722

Max Act: 5.8050. Min Act: -0.0000

Data Index: 758169 (C4 (Web Text))

Max Activating Token Index: 720

Text #14

Max Range: 7.5722. Min Range: -7.5722

Max Act: 5.6219. Min Act: -0.0000

Data Index: 935779 (C4 (Web Text))

Max Activating Token Index: 823

Text #15

Max Range: 7.5722. Min Range: -7.5722

Max Act: 5.5665. Min Act: -0.0000

Data Index: 106931 (C4 (Web Text))

Max Activating Token Index: 1000

Text #16

Max Range: 7.5722. Min Range: -7.5722

Max Act: 5.3232. Min Act: -0.0000

Data Index: 896652 (C4 (Web Text))

Max Activating Token Index: 617

Text #17

Max Range: 7.5722. Min Range: -7.5722

Max Act: 5.5031. Min Act: -0.0000

Data Index: 600536 (C4 (Web Text))

Max Activating Token Index: 778

Text #18

Max Range: 7.5722. Min Range: -7.5722

Max Act: 5.4559. Min Act: -0.0000

Data Index: 67117 (C4 (Web Text))

Max Activating Token Index: 502

Text #19

Max Range: 7.5722. Min Range: -7.5722

Max Act: 5.4622. Min Act: -0.0000

Data Index: 678098 (C4 (Web Text))

Max Activating Token Index: 95