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

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

Neuron 3453 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0853. Min Range: -5.0853

Max Act: 5.0853. Min Act: -0.0001

Data Index: 389658 (C4 (Web Text))

Max Activating Token Index: 692

Text #1

Max Range: 5.0853. Min Range: -5.0853

Max Act: 4.6737. Min Act: -0.0000

Data Index: 454614 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 5.0853. Min Range: -5.0853

Max Act: 4.7426. Min Act: -0.0000

Data Index: 214397 (C4 (Web Text))

Max Activating Token Index: 135

Text #3

Max Range: 5.0853. Min Range: -5.0853

Max Act: 4.6572. Min Act: -0.0000

Data Index: 611622 (C4 (Web Text))

Max Activating Token Index: 625

Text #4

Max Range: 5.0853. Min Range: -5.0853

Max Act: 4.4751. Min Act: -0.0000

Data Index: 1088184 (C4 (Web Text))

Max Activating Token Index: 967

Text #5

Max Range: 5.0853. Min Range: -5.0853

Max Act: 4.4306. Min Act: -0.0000

Data Index: 718961 (C4 (Web Text))

Max Activating Token Index: 381

Text #6

Max Range: 5.0853. Min Range: -5.0853

Max Act: 4.3621. Min Act: -0.0000

Data Index: 349478 (C4 (Web Text))

Max Activating Token Index: 456

Text #7

Max Range: 5.0853. Min Range: -5.0853

Max Act: 4.3448. Min Act: -0.0000

Data Index: 1109192 (C4 (Web Text))

Max Activating Token Index: 379

Text #8

Max Range: 5.0853. Min Range: -5.0853

Max Act: 4.2115. Min Act: -0.0000

Data Index: 833897 (C4 (Web Text))

Max Activating Token Index: 672

Text #9

Max Range: 5.0853. Min Range: -5.0853

Max Act: 3.9772. Min Act: -0.0000

Data Index: 761575 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 5.0853. Min Range: -5.0853

Max Act: 4.0317. Min Act: -0.0000

Data Index: 719528 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 5.0853. Min Range: -5.0853

Max Act: 3.9059. Min Act: -0.0000

Data Index: 811284 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 5.0853. Min Range: -5.0853

Max Act: 3.8907. Min Act: -0.0000

Data Index: 1346700 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 5.0853. Min Range: -5.0853

Max Act: 3.8149. Min Act: -0.0000

Data Index: 853858 (C4 (Web Text))

Max Activating Token Index: 75

Text #14

Max Range: 5.0853. Min Range: -5.0853

Max Act: 3.6753. Min Act: -0.0000

Data Index: 630653 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 5.0853. Min Range: -5.0853

Max Act: 3.6534. Min Act: -0.0000

Data Index: 56020 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 5.0853. Min Range: -5.0853

Max Act: 3.6542. Min Act: -0.0000

Data Index: 36166 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 5.0853. Min Range: -5.0853

Max Act: 3.5816. Min Act: -0.0000

Data Index: 385662 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 5.0853. Min Range: -5.0853

Max Act: 3.5490. Min Act: -0.0000

Data Index: 935457 (C4 (Web Text))

Max Activating Token Index: 971

Text #19

Max Range: 5.0853. Min Range: -5.0853

Max Act: 3.5174. Min Act: -0.0000

Data Index: 1045709 (C4 (Web Text))

Max Activating Token Index: 721