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

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

Neuron 4307 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: 5.4715. Min Range: -5.4715

Max Act: 5.4715. Min Act: -0.0000

Data Index: 1039210 (C4 (Web Text))

Max Activating Token Index: 871

Text #1

Max Range: 5.4715. Min Range: -5.4715

Max Act: 4.8352. Min Act: -0.0000

Data Index: 339819 (C4 (Web Text))

Max Activating Token Index: 511

Text #2

Max Range: 5.4715. Min Range: -5.4715

Max Act: 4.6833. Min Act: -0.0000

Data Index: 568191 (C4 (Web Text))

Max Activating Token Index: 511

Text #3

Max Range: 5.4715. Min Range: -5.4715

Max Act: 4.6254. Min Act: -0.0000

Data Index: 1307507 (C4 (Web Text))

Max Activating Token Index: 703

Text #4

Max Range: 5.4715. Min Range: -5.4715

Max Act: 4.7904. Min Act: -0.0000

Data Index: 662070 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 5.4715. Min Range: -5.4715

Max Act: 4.6102. Min Act: -0.0000

Data Index: 96768 (C4 (Web Text))

Max Activating Token Index: 1001

Text #6

Max Range: 5.4715. Min Range: -5.4715

Max Act: 4.6182. Min Act: -0.0000

Data Index: 280385 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 5.4715. Min Range: -5.4715

Max Act: 4.6789. Min Act: -0.0000

Data Index: 400552 (C4 (Web Text))

Max Activating Token Index: 560

Text #8

Max Range: 5.4715. Min Range: -5.4715

Max Act: 4.6885. Min Act: -0.0000

Data Index: 900158 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 5.4715. Min Range: -5.4715

Max Act: 4.3772. Min Act: -0.0000

Data Index: 298745 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 5.4715. Min Range: -5.4715

Max Act: 4.1499. Min Act: -0.0000

Data Index: 999943 (C4 (Web Text))

Max Activating Token Index: 992

Text #11

Max Range: 5.4715. Min Range: -5.4715

Max Act: 3.9566. Min Act: -0.0000

Data Index: 1094313 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 5.4715. Min Range: -5.4715

Max Act: 4.3116. Min Act: -0.0000

Data Index: 1197205 (C4 (Web Text))

Max Activating Token Index: 546

Text #13

Max Range: 5.4715. Min Range: -5.4715

Max Act: 4.3325. Min Act: -0.0000

Data Index: 194357 (C4 (Web Text))

Max Activating Token Index: 869

Text #14

Max Range: 5.4715. Min Range: -5.4715

Max Act: 4.1297. Min Act: -0.0000

Data Index: 260661 (C4 (Web Text))

Max Activating Token Index: 655

Text #15

Max Range: 5.4715. Min Range: -5.4715

Max Act: 4.2987. Min Act: -0.0000

Data Index: 749325 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 5.4715. Min Range: -5.4715

Max Act: 4.2653. Min Act: -0.0000

Data Index: 643582 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 5.4715. Min Range: -5.4715

Max Act: 4.1111. Min Act: -0.0000

Data Index: 549225 (C4 (Web Text))

Max Activating Token Index: 987

Text #18

Max Range: 5.4715. Min Range: -5.4715

Max Act: 4.4208. Min Act: -0.0000

Data Index: 802487 (C4 (Web Text))

Max Activating Token Index: 388

Text #19

Max Range: 5.4715. Min Range: -5.4715

Max Act: 4.1959. Min Act: -0.0000

Data Index: 645130 (C4 (Web Text))

Max Activating Token Index: 308