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

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

Neuron 2270 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.6493. Min Act: -0.0000

Data Index: 7140 (C4 (Web Text))

Max Activating Token Index: 430

Text #1

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.6150. Min Act: -0.0000

Data Index: 772196 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.5726. Min Act: -0.0000

Data Index: 1321844 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.5868. Min Act: -0.0000

Data Index: 434040 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.5888. Min Act: -0.0000

Data Index: 275361 (C4 (Web Text))

Max Activating Token Index: 831

Text #5

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.6206. Min Act: -0.0000

Data Index: 541368 (C4 (Web Text))

Max Activating Token Index: 813

Text #6

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.5463. Min Act: -0.0001

Data Index: 111623 (C4 (Web Text))

Max Activating Token Index: 627

Text #7

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.5918. Min Act: -0.0001

Data Index: 771045 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.5871. Min Act: -0.0000

Data Index: 506239 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.5459. Min Act: -0.0000

Data Index: 1328267 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.5647. Min Act: -0.0001

Data Index: 1132929 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.5855. Min Act: -0.0000

Data Index: 41793 (C4 (Web Text))

Max Activating Token Index: 255

Text #12

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.5421. Min Act: -0.0001

Data Index: 1045287 (C4 (Web Text))

Max Activating Token Index: 432

Text #13

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.5600. Min Act: -0.0001

Data Index: 27889 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.5734. Min Act: -0.0000

Data Index: 817617 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.5564. Min Act: -0.0000

Data Index: 291694 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.5338. Min Act: -0.0001

Data Index: 1009783 (C4 (Web Text))

Max Activating Token Index: 570

Text #17

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.5850. Min Act: -0.0000

Data Index: 1245476 (C4 (Web Text))

Max Activating Token Index: 979

Text #18

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.4952. Min Act: -0.0000

Data Index: 1056709 (C4 (Web Text))

Max Activating Token Index: 959

Text #19

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.5443. Min Act: -0.0000

Data Index: 695676 (C4 (Web Text))

Max Activating Token Index: 520