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

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

Neuron 4235 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1348. Min Range: -1.1348

Max Act: 1.1348. Min Act: -0.0000

Data Index: 694861 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 1.1348. Min Range: -1.1348

Max Act: 0.9287. Min Act: -0.0000

Data Index: 538736 (C4 (Web Text))

Max Activating Token Index: 449

Text #2

Max Range: 1.1348. Min Range: -1.1348

Max Act: 0.8843. Min Act: -0.0000

Data Index: 761747 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 1.1348. Min Range: -1.1348

Max Act: 0.8852. Min Act: -0.0000

Data Index: 1030315 (C4 (Web Text))

Max Activating Token Index: 639

Text #4

Max Range: 1.1348. Min Range: -1.1348

Max Act: 0.9335. Min Act: -0.0000

Data Index: 453913 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 1.1348. Min Range: -1.1348

Max Act: 0.8591. Min Act: -0.0000

Data Index: 302818 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 1.1348. Min Range: -1.1348

Max Act: 0.9202. Min Act: -0.0000

Data Index: 283897 (C4 (Web Text))

Max Activating Token Index: 724

Text #7

Max Range: 1.1348. Min Range: -1.1348

Max Act: 0.8309. Min Act: -0.0000

Data Index: 620686 (C4 (Web Text))

Max Activating Token Index: 269

Text #8

Max Range: 1.1348. Min Range: -1.1348

Max Act: 0.8302. Min Act: -0.0000

Data Index: 67038 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 1.1348. Min Range: -1.1348

Max Act: 0.8546. Min Act: -0.0000

Data Index: 803668 (C4 (Web Text))

Max Activating Token Index: 982

Text #10

Max Range: 1.1348. Min Range: -1.1348

Max Act: 0.8742. Min Act: -0.0000

Data Index: 884465 (C4 (Web Text))

Max Activating Token Index: 497

Text #11

Max Range: 1.1348. Min Range: -1.1348

Max Act: 0.7913. Min Act: -0.0000

Data Index: 1302677 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 1.1348. Min Range: -1.1348

Max Act: 0.8900. Min Act: -0.0000

Data Index: 18929 (C4 (Web Text))

Max Activating Token Index: 991

Text #13

Max Range: 1.1348. Min Range: -1.1348

Max Act: 0.7855. Min Act: -0.0000

Data Index: 1141912 (C4 (Web Text))

Max Activating Token Index: 835

Text #14

Max Range: 1.1348. Min Range: -1.1348

Max Act: 0.8264. Min Act: -0.0000

Data Index: 358300 (C4 (Web Text))

Max Activating Token Index: 462

Text #15

Max Range: 1.1348. Min Range: -1.1348

Max Act: 0.7977. Min Act: -0.0000

Data Index: 476586 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 1.1348. Min Range: -1.1348

Max Act: 0.7911. Min Act: -0.0000

Data Index: 1162721 (C4 (Web Text))

Max Activating Token Index: 928

Text #17

Max Range: 1.1348. Min Range: -1.1348

Max Act: 0.7595. Min Act: -0.0000

Data Index: 24446 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 1.1348. Min Range: -1.1348

Max Act: 0.7556. Min Act: -0.0000

Data Index: 353414 (C4 (Web Text))

Max Activating Token Index: 40

Text #19

Max Range: 1.1348. Min Range: -1.1348

Max Act: 0.8228. Min Act: -0.0000

Data Index: 17105 (C4 (Web Text))

Max Activating Token Index: 307