Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3680 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.6305. Min Act: -0.0002

Data Index: 671686 (C4 (Web Text))

Max Activating Token Index: 660

Text #1

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.6367. Min Act: -0.0002

Data Index: 1215238 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.5255. Min Act: -0.0002

Data Index: 892847 (C4 (Web Text))

Max Activating Token Index: 780

Text #3

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.4837. Min Act: -0.0002

Data Index: 453801 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.4537. Min Act: -0.0002

Data Index: 1062716 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.4940. Min Act: -0.0002

Data Index: 750582 (C4 (Web Text))

Max Activating Token Index: 627

Text #6

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.4871. Min Act: -0.0001

Data Index: 275144 (C4 (Web Text))

Max Activating Token Index: 65

Text #7

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.4008. Min Act: -0.0001

Data Index: 539671 (C4 (Web Text))

Max Activating Token Index: 228

Text #8

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.3141. Min Act: -0.0001

Data Index: 673212 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.3935. Min Act: -0.0001

Data Index: 678986 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.4592. Min Act: -0.0002

Data Index: 749188 (C4 (Web Text))

Max Activating Token Index: 923

Text #11

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.3287. Min Act: -0.0001

Data Index: 606830 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.4843. Min Act: -0.0001

Data Index: 825562 (C4 (Web Text))

Max Activating Token Index: 826

Text #13

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.3260. Min Act: -0.0001

Data Index: 531157 (C4 (Web Text))

Max Activating Token Index: 576

Text #14

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.3527. Min Act: -0.0001

Data Index: 545991 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.3538. Min Act: -0.0002

Data Index: 530093 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.3207. Min Act: -0.0001

Data Index: 664513 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.3724. Min Act: -0.0002

Data Index: 1051493 (C4 (Web Text))

Max Activating Token Index: 385

Text #18

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.3732. Min Act: -0.0002

Data Index: 1247798 (C4 (Web Text))

Max Activating Token Index: 481

Text #19

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.3799. Min Act: -0.0001

Data Index: 1060118 (C4 (Web Text))

Max Activating Token Index: 43