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

Dataset: The Pile

Neuron 2660 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.3952. Min Act: -0.0000

Data Index: 1680666 (The Pile)

Max Activating Token Index: 71

Text #1

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.4242. Min Act: -0.0000

Data Index: 927624 (The Pile)

Max Activating Token Index: 37

Text #2

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.2856. Min Act: -0.0000

Data Index: 458989 (The Pile)

Max Activating Token Index: 793

Text #3

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.2726. Min Act: -0.0000

Data Index: 1124166 (The Pile)

Max Activating Token Index: 896

Text #4

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.3417. Min Act: -0.0001

Data Index: 1808871 (The Pile)

Max Activating Token Index: 849

Text #5

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.3049. Min Act: -0.0000

Data Index: 1454996 (The Pile)

Max Activating Token Index: 187

Text #6

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.2476. Min Act: -0.0000

Data Index: 1248324 (The Pile)

Max Activating Token Index: 611

Text #7

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.1606. Min Act: -0.0000

Data Index: 1471891 (The Pile)

Max Activating Token Index: 807

Text #8

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.1536. Min Act: -0.0000

Data Index: 1193609 (The Pile)

Max Activating Token Index: 359

Text #9

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.1040. Min Act: -0.0000

Data Index: 319474 (The Pile)

Max Activating Token Index: 881

Text #10

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.1672. Min Act: -0.0000

Data Index: 442861 (The Pile)

Max Activating Token Index: 120

Text #11

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.1647. Min Act: -0.0000

Data Index: 1824818 (The Pile)

Max Activating Token Index: 349

Text #12

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.1529. Min Act: -0.0000

Data Index: 198542 (The Pile)

Max Activating Token Index: 875

Text #13

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.1081. Min Act: -0.0000

Data Index: 1052967 (The Pile)

Max Activating Token Index: 226

Text #14

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.1669. Min Act: -0.0000

Data Index: 1581539 (The Pile)

Max Activating Token Index: 173

Text #15

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.0987. Min Act: -0.0000

Data Index: 430559 (The Pile)

Max Activating Token Index: 497

Text #16

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.0845. Min Act: -0.0000

Data Index: 1365835 (The Pile)

Max Activating Token Index: 584

Text #17

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.0774. Min Act: -0.0000

Data Index: 1208353 (The Pile)

Max Activating Token Index: 446

Text #18

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.0326. Min Act: -0.0000

Data Index: 1203359 (The Pile)

Max Activating Token Index: 737

Text #19

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.1029. Min Act: -0.0000

Data Index: 239609 (The Pile)

Max Activating Token Index: 655