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

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

Neuron 660 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3513. Min Range: -1.3513

Max Act: 1.2961. Min Act: -0.0000

Data Index: 492628 (C4 (Web Text))

Max Activating Token Index: 162

Text #1

Max Range: 1.3513. Min Range: -1.3513

Max Act: 1.2857. Min Act: -0.0001

Data Index: 450135 (C4 (Web Text))

Max Activating Token Index: 445

Text #2

Max Range: 1.3513. Min Range: -1.3513

Max Act: 1.3513. Min Act: -0.0000

Data Index: 123765 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 1.3513. Min Range: -1.3513

Max Act: 1.2801. Min Act: -0.0000

Data Index: 681703 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 1.3513. Min Range: -1.3513

Max Act: 1.2981. Min Act: -0.0000

Data Index: 347477 (C4 (Web Text))

Max Activating Token Index: 530

Text #5

Max Range: 1.3513. Min Range: -1.3513

Max Act: 1.2047. Min Act: -0.0000

Data Index: 198077 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 1.3513. Min Range: -1.3513

Max Act: 1.2079. Min Act: -0.0001

Data Index: 820156 (C4 (Web Text))

Max Activating Token Index: 369

Text #7

Max Range: 1.3513. Min Range: -1.3513

Max Act: 1.1229. Min Act: -0.0001

Data Index: 716663 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 1.3513. Min Range: -1.3513

Max Act: 1.0887. Min Act: -0.0000

Data Index: 707222 (C4 (Web Text))

Max Activating Token Index: 413

Text #9

Max Range: 1.3513. Min Range: -1.3513

Max Act: 1.0429. Min Act: -0.0000

Data Index: 1111261 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 1.3513. Min Range: -1.3513

Max Act: 1.0428. Min Act: -0.0001

Data Index: 817771 (C4 (Web Text))

Max Activating Token Index: 827

Text #11

Max Range: 1.3513. Min Range: -1.3513

Max Act: 1.1418. Min Act: -0.0000

Data Index: 1024720 (C4 (Web Text))

Max Activating Token Index: 629

Text #12

Max Range: 1.3513. Min Range: -1.3513

Max Act: 1.0568. Min Act: -0.0001

Data Index: 118537 (C4 (Web Text))

Max Activating Token Index: 334

Text #13

Max Range: 1.3513. Min Range: -1.3513

Max Act: 1.0483. Min Act: -0.0000

Data Index: 629484 (C4 (Web Text))

Max Activating Token Index: 823

Text #14

Max Range: 1.3513. Min Range: -1.3513

Max Act: 1.0483. Min Act: -0.0001

Data Index: 1115445 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 1.3513. Min Range: -1.3513

Max Act: 1.0125. Min Act: -0.0001

Data Index: 166177 (C4 (Web Text))

Max Activating Token Index: 16

Text #16

Max Range: 1.3513. Min Range: -1.3513

Max Act: 1.0064. Min Act: -0.0000

Data Index: 1274769 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 1.3513. Min Range: -1.3513

Max Act: 1.0012. Min Act: -0.0001

Data Index: 876340 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 1.3513. Min Range: -1.3513

Max Act: 1.0365. Min Act: -0.0000

Data Index: 819093 (C4 (Web Text))

Max Activating Token Index: 690

Text #19

Max Range: 1.3513. Min Range: -1.3513

Max Act: 1.0681. Min Act: -0.0001

Data Index: 642354 (C4 (Web Text))

Max Activating Token Index: 361