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

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

Neuron 2711 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: 2.6160. Min Range: -2.6160

Max Act: 2.5111. Min Act: -0.0000

Data Index: 1163935 (C4 (Web Text))

Max Activating Token Index: 916

Text #1

Max Range: 2.6160. Min Range: -2.6160

Max Act: 2.5200. Min Act: -0.0000

Data Index: 482696 (C4 (Web Text))

Max Activating Token Index: 467

Text #2

Max Range: 2.6160. Min Range: -2.6160

Max Act: 2.5186. Min Act: -0.0000

Data Index: 676056 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 2.6160. Min Range: -2.6160

Max Act: 2.6160. Min Act: -0.0000

Data Index: 138656 (C4 (Web Text))

Max Activating Token Index: 965

Text #4

Max Range: 2.6160. Min Range: -2.6160

Max Act: 2.4328. Min Act: -0.0000

Data Index: 149421 (C4 (Web Text))

Max Activating Token Index: 966

Text #5

Max Range: 2.6160. Min Range: -2.6160

Max Act: 2.4459. Min Act: -0.0000

Data Index: 113651 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 2.6160. Min Range: -2.6160

Max Act: 2.3588. Min Act: -0.0000

Data Index: 1280072 (C4 (Web Text))

Max Activating Token Index: 762

Text #7

Max Range: 2.6160. Min Range: -2.6160

Max Act: 2.2338. Min Act: -0.0000

Data Index: 452980 (C4 (Web Text))

Max Activating Token Index: 314

Text #8

Max Range: 2.6160. Min Range: -2.6160

Max Act: 2.2003. Min Act: -0.0000

Data Index: 1351114 (C4 (Web Text))

Max Activating Token Index: 986

Text #9

Max Range: 2.6160. Min Range: -2.6160

Max Act: 2.2721. Min Act: -0.0000

Data Index: 86649 (C4 (Web Text))

Max Activating Token Index: 1012

Text #10

Max Range: 2.6160. Min Range: -2.6160

Max Act: 2.2858. Min Act: -0.0000

Data Index: 718186 (C4 (Web Text))

Max Activating Token Index: 885

Text #11

Max Range: 2.6160. Min Range: -2.6160

Max Act: 2.2267. Min Act: -0.0000

Data Index: 94459 (C4 (Web Text))

Max Activating Token Index: 618

Text #12

Max Range: 2.6160. Min Range: -2.6160

Max Act: 2.2164. Min Act: -0.0000

Data Index: 721686 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 2.6160. Min Range: -2.6160

Max Act: 2.2248. Min Act: -0.0000

Data Index: 1047784 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 2.6160. Min Range: -2.6160

Max Act: 2.1303. Min Act: -0.0000

Data Index: 277472 (C4 (Web Text))

Max Activating Token Index: 479

Text #15

Max Range: 2.6160. Min Range: -2.6160

Max Act: 1.9863. Min Act: -0.0000

Data Index: 1347222 (C4 (Web Text))

Max Activating Token Index: 868

Text #16

Max Range: 2.6160. Min Range: -2.6160

Max Act: 2.0875. Min Act: -0.0000

Data Index: 844804 (C4 (Web Text))

Max Activating Token Index: 616

Text #17

Max Range: 2.6160. Min Range: -2.6160

Max Act: 2.2016. Min Act: -0.0000

Data Index: 1056688 (C4 (Web Text))

Max Activating Token Index: 851

Text #18

Max Range: 2.6160. Min Range: -2.6160

Max Act: 2.1773. Min Act: -0.0000

Data Index: 578304 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 2.6160. Min Range: -2.6160

Max Act: 1.9501. Min Act: -0.0000

Data Index: 231541 (C4 (Web Text))

Max Activating Token Index: 434