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

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

Neuron 2678 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1711. Min Range: -1.1711

Max Act: 1.1631. Min Act: -0.0000

Data Index: 1125504 (C4 (Web Text))

Max Activating Token Index: 702

Text #1

Max Range: 1.1711. Min Range: -1.1711

Max Act: 1.0662. Min Act: -0.0000

Data Index: 35539 (C4 (Web Text))

Max Activating Token Index: 626

Text #2

Max Range: 1.1711. Min Range: -1.1711

Max Act: 1.0527. Min Act: -0.0000

Data Index: 691623 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 1.1711. Min Range: -1.1711

Max Act: 1.0395. Min Act: -0.0000

Data Index: 157823 (C4 (Web Text))

Max Activating Token Index: 341

Text #4

Max Range: 1.1711. Min Range: -1.1711

Max Act: 1.0724. Min Act: -0.0000

Data Index: 774497 (C4 (Web Text))

Max Activating Token Index: 926

Text #5

Max Range: 1.1711. Min Range: -1.1711

Max Act: 1.0519. Min Act: -0.0000

Data Index: 424024 (C4 (Web Text))

Max Activating Token Index: 815

Text #6

Max Range: 1.1711. Min Range: -1.1711

Max Act: 1.1711. Min Act: -0.0000

Data Index: 266283 (C4 (Web Text))

Max Activating Token Index: 734

Text #7

Max Range: 1.1711. Min Range: -1.1711

Max Act: 1.1362. Min Act: -0.0000

Data Index: 739076 (C4 (Web Text))

Max Activating Token Index: 685

Text #8

Max Range: 1.1711. Min Range: -1.1711

Max Act: 1.0647. Min Act: -0.0000

Data Index: 1257903 (C4 (Web Text))

Max Activating Token Index: 939

Text #9

Max Range: 1.1711. Min Range: -1.1711

Max Act: 1.0181. Min Act: -0.0000

Data Index: 856828 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 1.1711. Min Range: -1.1711

Max Act: 1.0549. Min Act: -0.0000

Data Index: 1357990 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 1.1711. Min Range: -1.1711

Max Act: 1.0793. Min Act: -0.0000

Data Index: 38366 (C4 (Web Text))

Max Activating Token Index: 975

Text #12

Max Range: 1.1711. Min Range: -1.1711

Max Act: 1.0330. Min Act: -0.0000

Data Index: 1274548 (C4 (Web Text))

Max Activating Token Index: 81

Text #13

Max Range: 1.1711. Min Range: -1.1711

Max Act: 1.0541. Min Act: -0.0000

Data Index: 960506 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 1.1711. Min Range: -1.1711

Max Act: 1.0541. Min Act: -0.0000

Data Index: 955001 (C4 (Web Text))

Max Activating Token Index: 430

Text #15

Max Range: 1.1711. Min Range: -1.1711

Max Act: 1.0826. Min Act: -0.0000

Data Index: 548542 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 1.1711. Min Range: -1.1711

Max Act: 0.9448. Min Act: -0.0000

Data Index: 1018446 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 1.1711. Min Range: -1.1711

Max Act: 1.0601. Min Act: -0.0000

Data Index: 1335367 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 1.1711. Min Range: -1.1711

Max Act: 0.8426. Min Act: -0.0000

Data Index: 270195 (C4 (Web Text))

Max Activating Token Index: 587

Text #19

Max Range: 1.1711. Min Range: -1.1711

Max Act: 0.9814. Min Act: -0.0000

Data Index: 854071 (C4 (Web Text))

Max Activating Token Index: 546