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

Dataset: The Pile

Neuron 1191 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.6394. Min Act: -0.0000

Data Index: 607876 (The Pile)

Max Activating Token Index: 101

Text #1

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.6645. Min Act: -0.0000

Data Index: 127233 (The Pile)

Max Activating Token Index: 861

Text #2

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5748. Min Act: -0.0000

Data Index: 1709564 (The Pile)

Max Activating Token Index: 760

Text #3

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5476. Min Act: -0.0000

Data Index: 1963283 (The Pile)

Max Activating Token Index: 121

Text #4

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.6351. Min Act: -0.0000

Data Index: 1259214 (The Pile)

Max Activating Token Index: 758

Text #5

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5004. Min Act: -0.0000

Data Index: 1456154 (The Pile)

Max Activating Token Index: 42

Text #6

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5759. Min Act: -0.0000

Data Index: 527613 (The Pile)

Max Activating Token Index: 654

Text #7

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5565. Min Act: -0.0000

Data Index: 1467390 (The Pile)

Max Activating Token Index: 776

Text #8

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5839. Min Act: -0.0000

Data Index: 1889636 (The Pile)

Max Activating Token Index: 529

Text #9

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5506. Min Act: -0.0000

Data Index: 24589 (The Pile)

Max Activating Token Index: 28

Text #10

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5786. Min Act: -0.0000

Data Index: 1121237 (The Pile)

Max Activating Token Index: 1017

Text #11

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5758. Min Act: -0.0000

Data Index: 252056 (The Pile)

Max Activating Token Index: 1001

Text #12

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5897. Min Act: -0.0000

Data Index: 7570 (The Pile)

Max Activating Token Index: 765

Text #13

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5199. Min Act: -0.0000

Data Index: 298860 (The Pile)

Max Activating Token Index: 149

Text #14

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5326. Min Act: -0.0000

Data Index: 821255 (The Pile)

Max Activating Token Index: 413

Text #15

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5411. Min Act: -0.0000

Data Index: 170944 (The Pile)

Max Activating Token Index: 647

Text #16

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4746. Min Act: -0.0000

Data Index: 812764 (The Pile)

Max Activating Token Index: 236

Text #17

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5338. Min Act: -0.0000

Data Index: 1401749 (The Pile)

Max Activating Token Index: 477

Text #18

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5603. Min Act: -0.0000

Data Index: 446047 (The Pile)

Max Activating Token Index: 331

Text #19

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5583. Min Act: -0.0000

Data Index: 1263017 (The Pile)

Max Activating Token Index: 772