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

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

Neuron 4173 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0650. Min Act: -0.0002

Data Index: 468700 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0653. Min Act: -0.0002

Data Index: 69676 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0649. Min Act: -0.0002

Data Index: 549649 (C4 (Web Text))

Max Activating Token Index: 619

Text #3

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0584. Min Act: -0.0002

Data Index: 1358353 (C4 (Web Text))

Max Activating Token Index: 843

Text #4

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0562. Min Act: -0.0002

Data Index: 947780 (C4 (Web Text))

Max Activating Token Index: 372

Text #5

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0574. Min Act: -0.0002

Data Index: 1127337 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0537. Min Act: -0.0002

Data Index: 337215 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0516. Min Act: -0.0002

Data Index: 1183763 (C4 (Web Text))

Max Activating Token Index: 480

Text #8

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0541. Min Act: -0.0002

Data Index: 271208 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0500. Min Act: -0.0002

Data Index: 14950 (C4 (Web Text))

Max Activating Token Index: 261

Text #10

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0525. Min Act: -0.0002

Data Index: 849082 (C4 (Web Text))

Max Activating Token Index: 215

Text #11

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0513. Min Act: -0.0002

Data Index: 601118 (C4 (Web Text))

Max Activating Token Index: 571

Text #12

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0510. Min Act: -0.0002

Data Index: 178652 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0511. Min Act: -0.0002

Data Index: 715551 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0482. Min Act: -0.0002

Data Index: 740095 (C4 (Web Text))

Max Activating Token Index: 973

Text #15

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1083726 (C4 (Web Text))

Max Activating Token Index: 834

Text #16

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0538. Min Act: -0.0002

Data Index: 532241 (C4 (Web Text))

Max Activating Token Index: 151

Text #17

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0470. Min Act: -0.0002

Data Index: 771068 (C4 (Web Text))

Max Activating Token Index: 281

Text #18

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0499. Min Act: -0.0002

Data Index: 378675 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0469. Min Act: -0.0002

Data Index: 440220 (C4 (Web Text))

Max Activating Token Index: 800