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

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

Neuron 3815 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0537. Min Act: -0.0000

Data Index: 566331 (C4 (Web Text))

Max Activating Token Index: 517

Text #1

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0489. Min Act: -0.0000

Data Index: 516879 (C4 (Web Text))

Max Activating Token Index: 726

Text #2

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0477. Min Act: -0.0000

Data Index: 260719 (C4 (Web Text))

Max Activating Token Index: 762

Text #3

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0469. Min Act: -0.0000

Data Index: 70331 (C4 (Web Text))

Max Activating Token Index: 1005

Text #4

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0486. Min Act: -0.0000

Data Index: 438417 (C4 (Web Text))

Max Activating Token Index: 966

Text #5

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0475. Min Act: -0.0000

Data Index: 704586 (C4 (Web Text))

Max Activating Token Index: 210

Text #6

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0433. Min Act: -0.0000

Data Index: 890110 (C4 (Web Text))

Max Activating Token Index: 583

Text #7

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0471. Min Act: -0.0000

Data Index: 1466849 (Python Code)

Max Activating Token Index: 373

Text #8

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0365. Min Act: -0.0000

Data Index: 1343124 (C4 (Web Text))

Max Activating Token Index: 423

Text #9

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0367. Min Act: -0.0000

Data Index: 449772 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0376. Min Act: -0.0000

Data Index: 523422 (C4 (Web Text))

Max Activating Token Index: 959

Text #11

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0356. Min Act: -0.0000

Data Index: 1240482 (C4 (Web Text))

Max Activating Token Index: 73

Text #12

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0349. Min Act: -0.0000

Data Index: 739306 (C4 (Web Text))

Max Activating Token Index: 613

Text #13

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0372. Min Act: -0.0000

Data Index: 1374883 (Python Code)

Max Activating Token Index: 788

Text #14

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0346. Min Act: -0.0000

Data Index: 529149 (C4 (Web Text))

Max Activating Token Index: 151

Text #15

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0328. Min Act: -0.0000

Data Index: 902362 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0343. Min Act: -0.0000

Data Index: 866345 (C4 (Web Text))

Max Activating Token Index: 378

Text #17

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0329. Min Act: -0.0000

Data Index: 1306479 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0356. Min Act: -0.0000

Data Index: 572052 (C4 (Web Text))

Max Activating Token Index: 383

Text #19

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0352. Min Act: -0.0000

Data Index: 100146 (C4 (Web Text))

Max Activating Token Index: 34