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

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

Neuron 573 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1402. Min Range: -1.1402

Max Act: 1.1402. Min Act: -0.0001

Data Index: 422138 (C4 (Web Text))

Max Activating Token Index: 407

Text #1

Max Range: 1.1402. Min Range: -1.1402

Max Act: 1.0938. Min Act: -0.0000

Data Index: 1296975 (C4 (Web Text))

Max Activating Token Index: 288

Text #2

Max Range: 1.1402. Min Range: -1.1402

Max Act: 1.1184. Min Act: -0.0001

Data Index: 744499 (C4 (Web Text))

Max Activating Token Index: 572

Text #3

Max Range: 1.1402. Min Range: -1.1402

Max Act: 1.0528. Min Act: -0.0000

Data Index: 1175838 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 1.1402. Min Range: -1.1402

Max Act: 1.0798. Min Act: -0.0001

Data Index: 224125 (C4 (Web Text))

Max Activating Token Index: 650

Text #5

Max Range: 1.1402. Min Range: -1.1402

Max Act: 1.0178. Min Act: -0.0000

Data Index: 821899 (C4 (Web Text))

Max Activating Token Index: 980

Text #6

Max Range: 1.1402. Min Range: -1.1402

Max Act: 1.0635. Min Act: -0.0000

Data Index: 914000 (C4 (Web Text))

Max Activating Token Index: 657

Text #7

Max Range: 1.1402. Min Range: -1.1402

Max Act: 1.0584. Min Act: -0.0001

Data Index: 1054442 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 1.1402. Min Range: -1.1402

Max Act: 0.9988. Min Act: -0.0000

Data Index: 469426 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 1.1402. Min Range: -1.1402

Max Act: 1.0214. Min Act: -0.0000

Data Index: 239525 (C4 (Web Text))

Max Activating Token Index: 464

Text #10

Max Range: 1.1402. Min Range: -1.1402

Max Act: 0.9650. Min Act: -0.0000

Data Index: 100296 (C4 (Web Text))

Max Activating Token Index: 757

Text #11

Max Range: 1.1402. Min Range: -1.1402

Max Act: 1.0141. Min Act: -0.0001

Data Index: 663676 (C4 (Web Text))

Max Activating Token Index: 997

Text #12

Max Range: 1.1402. Min Range: -1.1402

Max Act: 0.9883. Min Act: -0.0001

Data Index: 303577 (C4 (Web Text))

Max Activating Token Index: 477

Text #13

Max Range: 1.1402. Min Range: -1.1402

Max Act: 0.9793. Min Act: -0.0000

Data Index: 80935 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 1.1402. Min Range: -1.1402

Max Act: 0.9817. Min Act: -0.0001

Data Index: 393697 (C4 (Web Text))

Max Activating Token Index: 667

Text #15

Max Range: 1.1402. Min Range: -1.1402

Max Act: 0.9806. Min Act: -0.0000

Data Index: 814656 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 1.1402. Min Range: -1.1402

Max Act: 1.0164. Min Act: -0.0001

Data Index: 654496 (C4 (Web Text))

Max Activating Token Index: 519

Text #17

Max Range: 1.1402. Min Range: -1.1402

Max Act: 0.9455. Min Act: -0.0000

Data Index: 988655 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 1.1402. Min Range: -1.1402

Max Act: 0.9286. Min Act: -0.0000

Data Index: 523903 (C4 (Web Text))

Max Activating Token Index: 472

Text #19

Max Range: 1.1402. Min Range: -1.1402

Max Act: 0.9337. Min Act: -0.0000

Data Index: 67704 (C4 (Web Text))

Max Activating Token Index: 728