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

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

Neuron 3670 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7849. Min Range: -2.7849

Max Act: 2.7849. Min Act: -0.0000

Data Index: 652630 (C4 (Web Text))

Max Activating Token Index: 461

Text #1

Max Range: 2.7849. Min Range: -2.7849

Max Act: 2.6586. Min Act: -0.0000

Data Index: 457931 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 2.7849. Min Range: -2.7849

Max Act: 2.6217. Min Act: -0.0000

Data Index: 1069933 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 2.7849. Min Range: -2.7849

Max Act: 2.4937. Min Act: 0.0000

Data Index: 608116 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 2.7849. Min Range: -2.7849

Max Act: 2.6034. Min Act: -0.0000

Data Index: 279134 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 2.7849. Min Range: -2.7849

Max Act: 2.4918. Min Act: -0.0000

Data Index: 991774 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 2.7849. Min Range: -2.7849

Max Act: 2.3757. Min Act: -0.0000

Data Index: 236869 (C4 (Web Text))

Max Activating Token Index: 667

Text #7

Max Range: 2.7849. Min Range: -2.7849

Max Act: 2.3850. Min Act: -0.0000

Data Index: 1244916 (C4 (Web Text))

Max Activating Token Index: 782

Text #8

Max Range: 2.7849. Min Range: -2.7849

Max Act: 2.3343. Min Act: -0.0000

Data Index: 1090496 (C4 (Web Text))

Max Activating Token Index: 470

Text #9

Max Range: 2.7849. Min Range: -2.7849

Max Act: 2.4045. Min Act: -0.0000

Data Index: 422090 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 2.7849. Min Range: -2.7849

Max Act: 2.1200. Min Act: -0.0000

Data Index: 580653 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 2.7849. Min Range: -2.7849

Max Act: 2.0850. Min Act: 0.0000

Data Index: 993542 (C4 (Web Text))

Max Activating Token Index: 409

Text #12

Max Range: 2.7849. Min Range: -2.7849

Max Act: 2.0387. Min Act: -0.0000

Data Index: 339318 (C4 (Web Text))

Max Activating Token Index: 459

Text #13

Max Range: 2.7849. Min Range: -2.7849

Max Act: 2.1178. Min Act: -0.0000

Data Index: 433449 (C4 (Web Text))

Max Activating Token Index: 827

Text #14

Max Range: 2.7849. Min Range: -2.7849

Max Act: 2.0534. Min Act: -0.0000

Data Index: 311025 (C4 (Web Text))

Max Activating Token Index: 814

Text #15

Max Range: 2.7849. Min Range: -2.7849

Max Act: 2.0382. Min Act: -0.0000

Data Index: 1035874 (C4 (Web Text))

Max Activating Token Index: 454

Text #16

Max Range: 2.7849. Min Range: -2.7849

Max Act: 2.0400. Min Act: 0.0000

Data Index: 918412 (C4 (Web Text))

Max Activating Token Index: 706

Text #17

Max Range: 2.7849. Min Range: -2.7849

Max Act: 2.0128. Min Act: -0.0000

Data Index: 704369 (C4 (Web Text))

Max Activating Token Index: 694

Text #18

Max Range: 2.7849. Min Range: -2.7849

Max Act: 2.1198. Min Act: -0.0000

Data Index: 1155492 (C4 (Web Text))

Max Activating Token Index: 407

Text #19

Max Range: 2.7849. Min Range: -2.7849

Max Act: 1.9957. Min Act: -0.0000

Data Index: 389466 (C4 (Web Text))

Max Activating Token Index: 766