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

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

Neuron 1700 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: 0.3634. Min Range: -0.3634

Max Act: 0.3582. Min Act: -0.0000

Data Index: 1060405 (C4 (Web Text))

Max Activating Token Index: 733

Text #1

Max Range: 0.3634. Min Range: -0.3634

Max Act: 0.3463. Min Act: -0.0000

Data Index: 1108659 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 0.3634. Min Range: -0.3634

Max Act: 0.3634. Min Act: -0.0000

Data Index: 131815 (C4 (Web Text))

Max Activating Token Index: 297

Text #3

Max Range: 0.3634. Min Range: -0.3634

Max Act: 0.3364. Min Act: -0.0000

Data Index: 331683 (C4 (Web Text))

Max Activating Token Index: 647

Text #4

Max Range: 0.3634. Min Range: -0.3634

Max Act: 0.3237. Min Act: -0.0000

Data Index: 729840 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 0.3634. Min Range: -0.3634

Max Act: 0.3118. Min Act: -0.0000

Data Index: 1089209 (C4 (Web Text))

Max Activating Token Index: 209

Text #6

Max Range: 0.3634. Min Range: -0.3634

Max Act: 0.2853. Min Act: -0.0000

Data Index: 780965 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 0.3634. Min Range: -0.3634

Max Act: 0.2623. Min Act: -0.0000

Data Index: 370256 (C4 (Web Text))

Max Activating Token Index: 531

Text #8

Max Range: 0.3634. Min Range: -0.3634

Max Act: 0.2760. Min Act: -0.0000

Data Index: 377459 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 0.3634. Min Range: -0.3634

Max Act: 0.2630. Min Act: -0.0000

Data Index: 658174 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 0.3634. Min Range: -0.3634

Max Act: 0.2527. Min Act: -0.0000

Data Index: 173508 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 0.3634. Min Range: -0.3634

Max Act: 0.2630. Min Act: -0.0000

Data Index: 945560 (C4 (Web Text))

Max Activating Token Index: 922

Text #12

Max Range: 0.3634. Min Range: -0.3634

Max Act: 0.2486. Min Act: -0.0000

Data Index: 162886 (C4 (Web Text))

Max Activating Token Index: 709

Text #13

Max Range: 0.3634. Min Range: -0.3634

Max Act: 0.2246. Min Act: -0.0000

Data Index: 104502 (C4 (Web Text))

Max Activating Token Index: 715

Text #14

Max Range: 0.3634. Min Range: -0.3634

Max Act: 0.2409. Min Act: -0.0000

Data Index: 783963 (C4 (Web Text))

Max Activating Token Index: 759

Text #15

Max Range: 0.3634. Min Range: -0.3634

Max Act: 0.2406. Min Act: -0.0000

Data Index: 1114810 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 0.3634. Min Range: -0.3634

Max Act: 0.2381. Min Act: -0.0000

Data Index: 428519 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 0.3634. Min Range: -0.3634

Max Act: 0.2361. Min Act: -0.0000

Data Index: 684727 (C4 (Web Text))

Max Activating Token Index: 691

Text #18

Max Range: 0.3634. Min Range: -0.3634

Max Act: 0.2292. Min Act: -0.0000

Data Index: 830630 (C4 (Web Text))

Max Activating Token Index: 340

Text #19

Max Range: 0.3634. Min Range: -0.3634

Max Act: 0.2368. Min Act: -0.0000

Data Index: 521127 (C4 (Web Text))

Max Activating Token Index: 832