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

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

Neuron 233 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0826. Min Act: -0.0000

Data Index: 1049508 (C4 (Web Text))

Max Activating Token Index: 937

Text #1

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0806. Min Act: -0.0000

Data Index: 1042649 (C4 (Web Text))

Max Activating Token Index: 471

Text #2

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0830. Min Act: -0.0000

Data Index: 825546 (C4 (Web Text))

Max Activating Token Index: 580

Text #3

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0731. Min Act: -0.0000

Data Index: 1340283 (C4 (Web Text))

Max Activating Token Index: 413

Text #4

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0698. Min Act: -0.0000

Data Index: 907129 (C4 (Web Text))

Max Activating Token Index: 537

Text #5

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0627. Min Act: -0.0000

Data Index: 336934 (C4 (Web Text))

Max Activating Token Index: 904

Text #6

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0441. Min Act: -0.0000

Data Index: 209526 (C4 (Web Text))

Max Activating Token Index: 172

Text #7

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0454. Min Act: -0.0000

Data Index: 58963 (C4 (Web Text))

Max Activating Token Index: 266

Text #8

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0402. Min Act: -0.0000

Data Index: 93712 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0401. Min Act: -0.0000

Data Index: 129020 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0384. Min Act: -0.0000

Data Index: 870224 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0384. Min Act: -0.0000

Data Index: 169057 (C4 (Web Text))

Max Activating Token Index: 918

Text #12

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0410. Min Act: -0.0000

Data Index: 878750 (C4 (Web Text))

Max Activating Token Index: 55

Text #13

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0353. Min Act: -0.0000

Data Index: 190096 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0362. Min Act: -0.0000

Data Index: 242316 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0355. Min Act: -0.0000

Data Index: 1600541 (Python Code)

Max Activating Token Index: 892

Text #16

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0349. Min Act: -0.0000

Data Index: 311295 (C4 (Web Text))

Max Activating Token Index: 482

Text #17

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0378. Min Act: -0.0000

Data Index: 1022624 (C4 (Web Text))

Max Activating Token Index: 332

Text #18

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0327. Min Act: -0.0000

Data Index: 827580 (C4 (Web Text))

Max Activating Token Index: 231

Text #19

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0341. Min Act: -0.0000

Data Index: 491352 (C4 (Web Text))

Max Activating Token Index: 771