Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1651 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.5459. Min Range: -1.5459

Max Act: 1.5213. Min Act: -0.0003

Data Index: 1182536 (C4 (Web Text))

Max Activating Token Index: 590

Text #1

Max Range: 1.5459. Min Range: -1.5459

Max Act: 1.5459. Min Act: -0.0003

Data Index: 1333360 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 1.5459. Min Range: -1.5459

Max Act: 1.4148. Min Act: -0.0003

Data Index: 305656 (C4 (Web Text))

Max Activating Token Index: 265

Text #3

Max Range: 1.5459. Min Range: -1.5459

Max Act: 1.4929. Min Act: -0.0003

Data Index: 1297694 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 1.5459. Min Range: -1.5459

Max Act: 1.3874. Min Act: -0.0003

Data Index: 795879 (C4 (Web Text))

Max Activating Token Index: 911

Text #5

Max Range: 1.5459. Min Range: -1.5459

Max Act: 1.3904. Min Act: -0.0003

Data Index: 777854 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 1.5459. Min Range: -1.5459

Max Act: 1.4193. Min Act: -0.0003

Data Index: 136173 (C4 (Web Text))

Max Activating Token Index: 93

Text #7

Max Range: 1.5459. Min Range: -1.5459

Max Act: 1.3491. Min Act: -0.0003

Data Index: 591780 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 1.5459. Min Range: -1.5459

Max Act: 1.3863. Min Act: -0.0003

Data Index: 1077101 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 1.5459. Min Range: -1.5459

Max Act: 1.3536. Min Act: -0.0003

Data Index: 868598 (C4 (Web Text))

Max Activating Token Index: 352

Text #10

Max Range: 1.5459. Min Range: -1.5459

Max Act: 1.1896. Min Act: -0.0003

Data Index: 1334758 (C4 (Web Text))

Max Activating Token Index: 34

Text #11

Max Range: 1.5459. Min Range: -1.5459

Max Act: 1.2163. Min Act: -0.0003

Data Index: 1107753 (C4 (Web Text))

Max Activating Token Index: 865

Text #12

Max Range: 1.5459. Min Range: -1.5459

Max Act: 1.2162. Min Act: -0.0003

Data Index: 105934 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 1.5459. Min Range: -1.5459

Max Act: 0.9555. Min Act: -0.0003

Data Index: 1017991 (C4 (Web Text))

Max Activating Token Index: 579

Text #14

Max Range: 1.5459. Min Range: -1.5459

Max Act: 0.9868. Min Act: -0.0003

Data Index: 702542 (C4 (Web Text))

Max Activating Token Index: 625

Text #15

Max Range: 1.5459. Min Range: -1.5459

Max Act: 1.1033. Min Act: -0.0003

Data Index: 70250 (C4 (Web Text))

Max Activating Token Index: 421

Text #16

Max Range: 1.5459. Min Range: -1.5459

Max Act: 1.0255. Min Act: -0.0003

Data Index: 97439 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 1.5459. Min Range: -1.5459

Max Act: 0.9968. Min Act: -0.0003

Data Index: 782835 (C4 (Web Text))

Max Activating Token Index: 704

Text #18

Max Range: 1.5459. Min Range: -1.5459

Max Act: 1.1155. Min Act: -0.0002

Data Index: 475534 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 1.5459. Min Range: -1.5459

Max Act: 1.0786. Min Act: -0.0003

Data Index: 1357179 (C4 (Web Text))

Max Activating Token Index: 274