Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 435 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0479. Min Act: -0.0006

Data Index: 138836 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0477. Min Act: -0.0006

Data Index: 963878 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0461. Min Act: -0.0005

Data Index: 945908 (C4 (Web Text))

Max Activating Token Index: 243

Text #3

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0452. Min Act: -0.0006

Data Index: 525311 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0441. Min Act: -0.0006

Data Index: 381354 (C4 (Web Text))

Max Activating Token Index: 722

Text #5

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0440. Min Act: -0.0006

Data Index: 93846 (C4 (Web Text))

Max Activating Token Index: 456

Text #6

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0438. Min Act: -0.0006

Data Index: 1347060 (C4 (Web Text))

Max Activating Token Index: 572

Text #7

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0420. Min Act: -0.0005

Data Index: 674707 (C4 (Web Text))

Max Activating Token Index: 741

Text #8

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0417. Min Act: -0.0005

Data Index: 108171 (C4 (Web Text))

Max Activating Token Index: 149

Text #9

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0409. Min Act: -0.0006

Data Index: 969682 (C4 (Web Text))

Max Activating Token Index: 568

Text #10

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0401. Min Act: -0.0005

Data Index: 1033102 (C4 (Web Text))

Max Activating Token Index: 511

Text #11

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0429. Min Act: -0.0006

Data Index: 460203 (C4 (Web Text))

Max Activating Token Index: 140

Text #12

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0409. Min Act: -0.0006

Data Index: 216833 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0386. Min Act: -0.0005

Data Index: 187396 (C4 (Web Text))

Max Activating Token Index: 543

Text #14

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0414. Min Act: -0.0006

Data Index: 1016326 (C4 (Web Text))

Max Activating Token Index: 592

Text #15

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0387. Min Act: -0.0005

Data Index: 619428 (C4 (Web Text))

Max Activating Token Index: 515

Text #16

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0417. Min Act: -0.0006

Data Index: 677744 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0365. Min Act: -0.0006

Data Index: 296447 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0387. Min Act: -0.0006

Data Index: 1016585 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0394. Min Act: -0.0005

Data Index: 291297 (C4 (Web Text))

Max Activating Token Index: 247