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

Dataset: The Pile

Neuron 2939 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5433. Min Range: -3.5433

Max Act: 3.4223. Min Act: -0.0000

Data Index: 535593 (The Pile)

Max Activating Token Index: 242

Text #1

Max Range: 3.5433. Min Range: -3.5433

Max Act: 3.5433. Min Act: -0.0000

Data Index: 897516 (The Pile)

Max Activating Token Index: 341

Text #2

Max Range: 3.5433. Min Range: -3.5433

Max Act: 3.1905. Min Act: -0.0000

Data Index: 1138505 (The Pile)

Max Activating Token Index: 234

Text #3

Max Range: 3.5433. Min Range: -3.5433

Max Act: 3.0450. Min Act: -0.0000

Data Index: 297323 (The Pile)

Max Activating Token Index: 561

Text #4

Max Range: 3.5433. Min Range: -3.5433

Max Act: 2.8895. Min Act: -0.0000

Data Index: 1944070 (The Pile)

Max Activating Token Index: 674

Text #5

Max Range: 3.5433. Min Range: -3.5433

Max Act: 3.1516. Min Act: -0.0000

Data Index: 1079648 (The Pile)

Max Activating Token Index: 491

Text #6

Max Range: 3.5433. Min Range: -3.5433

Max Act: 3.2845. Min Act: -0.0000

Data Index: 956432 (The Pile)

Max Activating Token Index: 497

Text #7

Max Range: 3.5433. Min Range: -3.5433

Max Act: 3.2682. Min Act: -0.0000

Data Index: 248490 (The Pile)

Max Activating Token Index: 72

Text #8

Max Range: 3.5433. Min Range: -3.5433

Max Act: 3.1017. Min Act: -0.0000

Data Index: 640260 (The Pile)

Max Activating Token Index: 174

Text #9

Max Range: 3.5433. Min Range: -3.5433

Max Act: 2.9591. Min Act: -0.0000

Data Index: 1470566 (The Pile)

Max Activating Token Index: 985

Text #10

Max Range: 3.5433. Min Range: -3.5433

Max Act: 2.9313. Min Act: -0.0000

Data Index: 1423409 (The Pile)

Max Activating Token Index: 869

Text #11

Max Range: 3.5433. Min Range: -3.5433

Max Act: 3.2041. Min Act: -0.0000

Data Index: 1803732 (The Pile)

Max Activating Token Index: 325

Text #12

Max Range: 3.5433. Min Range: -3.5433

Max Act: 3.1533. Min Act: -0.0000

Data Index: 818365 (The Pile)

Max Activating Token Index: 236

Text #13

Max Range: 3.5433. Min Range: -3.5433

Max Act: 3.0948. Min Act: -0.0000

Data Index: 235688 (The Pile)

Max Activating Token Index: 694

Text #14

Max Range: 3.5433. Min Range: -3.5433

Max Act: 2.7390. Min Act: -0.0000

Data Index: 1368324 (The Pile)

Max Activating Token Index: 480

Text #15

Max Range: 3.5433. Min Range: -3.5433

Max Act: 2.8161. Min Act: -0.0000

Data Index: 1163927 (The Pile)

Max Activating Token Index: 566

Text #16

Max Range: 3.5433. Min Range: -3.5433

Max Act: 2.8000. Min Act: -0.0000

Data Index: 1470496 (The Pile)

Max Activating Token Index: 286

Text #17

Max Range: 3.5433. Min Range: -3.5433

Max Act: 3.3931. Min Act: -0.0000

Data Index: 55852 (The Pile)

Max Activating Token Index: 1016

Text #18

Max Range: 3.5433. Min Range: -3.5433

Max Act: 3.0866. Min Act: -0.0000

Data Index: 996755 (The Pile)

Max Activating Token Index: 853

Text #19

Max Range: 3.5433. Min Range: -3.5433

Max Act: 2.9918. Min Act: -0.0000

Data Index: 1799484 (The Pile)

Max Activating Token Index: 775