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

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

Neuron 4289 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: 0.8359. Min Range: -0.8359

Max Act: 0.8359. Min Act: -0.0000

Data Index: 977063 (C4 (Web Text))

Max Activating Token Index: 270

Text #1

Max Range: 0.8359. Min Range: -0.8359

Max Act: 0.7526. Min Act: -0.0000

Data Index: 626757 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 0.8359. Min Range: -0.8359

Max Act: 0.8167. Min Act: -0.0000

Data Index: 641631 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 0.8359. Min Range: -0.8359

Max Act: 0.7326. Min Act: -0.0000

Data Index: 615471 (C4 (Web Text))

Max Activating Token Index: 534

Text #4

Max Range: 0.8359. Min Range: -0.8359

Max Act: 0.7114. Min Act: -0.0000

Data Index: 1002947 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 0.8359. Min Range: -0.8359

Max Act: 0.7056. Min Act: -0.0000

Data Index: 1108226 (C4 (Web Text))

Max Activating Token Index: 418

Text #6

Max Range: 0.8359. Min Range: -0.8359

Max Act: 0.6749. Min Act: -0.0000

Data Index: 834771 (C4 (Web Text))

Max Activating Token Index: 408

Text #7

Max Range: 0.8359. Min Range: -0.8359

Max Act: 0.6929. Min Act: -0.0000

Data Index: 719554 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 0.8359. Min Range: -0.8359

Max Act: 0.6902. Min Act: -0.0000

Data Index: 207484 (C4 (Web Text))

Max Activating Token Index: 490

Text #9

Max Range: 0.8359. Min Range: -0.8359

Max Act: 0.6348. Min Act: -0.0000

Data Index: 849568 (C4 (Web Text))

Max Activating Token Index: 203

Text #10

Max Range: 0.8359. Min Range: -0.8359

Max Act: 0.6583. Min Act: -0.0000

Data Index: 919421 (C4 (Web Text))

Max Activating Token Index: 64

Text #11

Max Range: 0.8359. Min Range: -0.8359

Max Act: 0.6153. Min Act: -0.0000

Data Index: 1005705 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 0.8359. Min Range: -0.8359

Max Act: 0.6100. Min Act: -0.0000

Data Index: 256592 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 0.8359. Min Range: -0.8359

Max Act: 0.6218. Min Act: -0.0000

Data Index: 837649 (C4 (Web Text))

Max Activating Token Index: 854

Text #14

Max Range: 0.8359. Min Range: -0.8359

Max Act: 0.6288. Min Act: -0.0000

Data Index: 64085 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 0.8359. Min Range: -0.8359

Max Act: 0.7307. Min Act: -0.0000

Data Index: 56113 (C4 (Web Text))

Max Activating Token Index: 683

Text #16

Max Range: 0.8359. Min Range: -0.8359

Max Act: 0.5709. Min Act: -0.0000

Data Index: 1039381 (C4 (Web Text))

Max Activating Token Index: 264

Text #17

Max Range: 0.8359. Min Range: -0.8359

Max Act: 0.6176. Min Act: -0.0000

Data Index: 20749 (C4 (Web Text))

Max Activating Token Index: 430

Text #18

Max Range: 0.8359. Min Range: -0.8359

Max Act: 0.6227. Min Act: -0.0000

Data Index: 1262867 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 0.8359. Min Range: -0.8359

Max Act: 0.5854. Min Act: -0.0000

Data Index: 564812 (C4 (Web Text))

Max Activating Token Index: 861