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

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

Neuron 479 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: 2.5564. Min Range: -2.5564

Max Act: 2.5564. Min Act: -0.0000

Data Index: 873406 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 2.5564. Min Range: -2.5564

Max Act: 2.0631. Min Act: -0.0000

Data Index: 153020 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 2.5564. Min Range: -2.5564

Max Act: 1.9479. Min Act: -0.0000

Data Index: 481220 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 2.5564. Min Range: -2.5564

Max Act: 1.7864. Min Act: -0.0000

Data Index: 1006858 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 2.5564. Min Range: -2.5564

Max Act: 1.7101. Min Act: -0.0000

Data Index: 112888 (C4 (Web Text))

Max Activating Token Index: 17

Text #5

Max Range: 2.5564. Min Range: -2.5564

Max Act: 1.5026. Min Act: -0.0000

Data Index: 1093599 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 2.5564. Min Range: -2.5564

Max Act: 1.3688. Min Act: -0.0000

Data Index: 722565 (C4 (Web Text))

Max Activating Token Index: 535

Text #7

Max Range: 2.5564. Min Range: -2.5564

Max Act: 1.4307. Min Act: -0.0000

Data Index: 866981 (C4 (Web Text))

Max Activating Token Index: 771

Text #8

Max Range: 2.5564. Min Range: -2.5564

Max Act: 1.3571. Min Act: -0.0000

Data Index: 476236 (C4 (Web Text))

Max Activating Token Index: 6

Text #9

Max Range: 2.5564. Min Range: -2.5564

Max Act: 1.3464. Min Act: -0.0000

Data Index: 1101381 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 2.5564. Min Range: -2.5564

Max Act: 1.3187. Min Act: 0.0001

Data Index: 9886 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 2.5564. Min Range: -2.5564

Max Act: 1.2940. Min Act: -0.0000

Data Index: 1016304 (C4 (Web Text))

Max Activating Token Index: 524

Text #12

Max Range: 2.5564. Min Range: -2.5564

Max Act: 1.2398. Min Act: -0.0000

Data Index: 161282 (C4 (Web Text))

Max Activating Token Index: 20

Text #13

Max Range: 2.5564. Min Range: -2.5564

Max Act: 1.2325. Min Act: -0.0000

Data Index: 438467 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 2.5564. Min Range: -2.5564

Max Act: 1.2245. Min Act: -0.0000

Data Index: 981839 (C4 (Web Text))

Max Activating Token Index: 511

Text #15

Max Range: 2.5564. Min Range: -2.5564

Max Act: 1.2292. Min Act: -0.0000

Data Index: 349120 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 2.5564. Min Range: -2.5564

Max Act: 1.2424. Min Act: -0.0000

Data Index: 1037162 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 2.5564. Min Range: -2.5564

Max Act: 1.1711. Min Act: -0.0000

Data Index: 966763 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 2.5564. Min Range: -2.5564

Max Act: 1.1350. Min Act: -0.0000

Data Index: 223441 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 2.5564. Min Range: -2.5564

Max Act: 1.2625. Min Act: -0.0000

Data Index: 613587 (C4 (Web Text))

Max Activating Token Index: 45