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

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

Neuron 5020 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0853. Min Range: -4.0853

Max Act: 4.0853. Min Act: -0.0000

Data Index: 761772 (C4 (Web Text))

Max Activating Token Index: 779

Text #1

Max Range: 4.0853. Min Range: -4.0853

Max Act: 3.7134. Min Act: -0.0000

Data Index: 1304497 (C4 (Web Text))

Max Activating Token Index: 964

Text #2

Max Range: 4.0853. Min Range: -4.0853

Max Act: 3.1874. Min Act: -0.0000

Data Index: 1216490 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 4.0853. Min Range: -4.0853

Max Act: 3.2740. Min Act: -0.0000

Data Index: 710313 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 4.0853. Min Range: -4.0853

Max Act: 2.9138. Min Act: -0.0000

Data Index: 854006 (C4 (Web Text))

Max Activating Token Index: 91

Text #5

Max Range: 4.0853. Min Range: -4.0853

Max Act: 2.7532. Min Act: -0.0000

Data Index: 512653 (C4 (Web Text))

Max Activating Token Index: 511

Text #6

Max Range: 4.0853. Min Range: -4.0853

Max Act: 2.8551. Min Act: -0.0000

Data Index: 588917 (C4 (Web Text))

Max Activating Token Index: 669

Text #7

Max Range: 4.0853. Min Range: -4.0853

Max Act: 2.7889. Min Act: -0.0000

Data Index: 287016 (C4 (Web Text))

Max Activating Token Index: 272

Text #8

Max Range: 4.0853. Min Range: -4.0853

Max Act: 2.7192. Min Act: -0.0000

Data Index: 491441 (C4 (Web Text))

Max Activating Token Index: 363

Text #9

Max Range: 4.0853. Min Range: -4.0853

Max Act: 2.7202. Min Act: -0.0000

Data Index: 100060 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 4.0853. Min Range: -4.0853

Max Act: 2.5088. Min Act: -0.0000

Data Index: 298040 (C4 (Web Text))

Max Activating Token Index: 592

Text #11

Max Range: 4.0853. Min Range: -4.0853

Max Act: 2.3300. Min Act: -0.0000

Data Index: 221094 (C4 (Web Text))

Max Activating Token Index: 109

Text #12

Max Range: 4.0853. Min Range: -4.0853

Max Act: 2.2862. Min Act: -0.0000

Data Index: 1345784 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 4.0853. Min Range: -4.0853

Max Act: 2.1582. Min Act: -0.0000

Data Index: 1015319 (C4 (Web Text))

Max Activating Token Index: 351

Text #14

Max Range: 4.0853. Min Range: -4.0853

Max Act: 2.1556. Min Act: -0.0000

Data Index: 963934 (C4 (Web Text))

Max Activating Token Index: 754

Text #15

Max Range: 4.0853. Min Range: -4.0853

Max Act: 2.2427. Min Act: -0.0000

Data Index: 948465 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 4.0853. Min Range: -4.0853

Max Act: 2.0973. Min Act: -0.0000

Data Index: 199193 (C4 (Web Text))

Max Activating Token Index: 897

Text #17

Max Range: 4.0853. Min Range: -4.0853

Max Act: 2.1624. Min Act: -0.0000

Data Index: 395144 (C4 (Web Text))

Max Activating Token Index: 289

Text #18

Max Range: 4.0853. Min Range: -4.0853

Max Act: 2.3856. Min Act: -0.0000

Data Index: 95925 (C4 (Web Text))

Max Activating Token Index: 811

Text #19

Max Range: 4.0853. Min Range: -4.0853

Max Act: 2.2517. Min Act: -0.0000

Data Index: 1157322 (C4 (Web Text))

Max Activating Token Index: 37