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

Dataset: The Pile

Neuron 1203 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4943. Min Range: -3.4943

Max Act: 3.4943. Min Act: -0.0000

Data Index: 358266 (The Pile)

Max Activating Token Index: 775

Text #1

Max Range: 3.4943. Min Range: -3.4943

Max Act: 3.3451. Min Act: -0.0000

Data Index: 338674 (The Pile)

Max Activating Token Index: 937

Text #2

Max Range: 3.4943. Min Range: -3.4943

Max Act: 3.1276. Min Act: -0.0000

Data Index: 1296827 (The Pile)

Max Activating Token Index: 1020

Text #3

Max Range: 3.4943. Min Range: -3.4943

Max Act: 3.0849. Min Act: -0.0000

Data Index: 194015 (The Pile)

Max Activating Token Index: 843

Text #4

Max Range: 3.4943. Min Range: -3.4943

Max Act: 2.7812. Min Act: -0.0000

Data Index: 1086995 (The Pile)

Max Activating Token Index: 735

Text #5

Max Range: 3.4943. Min Range: -3.4943

Max Act: 3.0607. Min Act: -0.0000

Data Index: 197761 (The Pile)

Max Activating Token Index: 566

Text #6

Max Range: 3.4943. Min Range: -3.4943

Max Act: 3.1135. Min Act: -0.0000

Data Index: 787132 (The Pile)

Max Activating Token Index: 578

Text #7

Max Range: 3.4943. Min Range: -3.4943

Max Act: 2.8048. Min Act: -0.0000

Data Index: 438601 (The Pile)

Max Activating Token Index: 986

Text #8

Max Range: 3.4943. Min Range: -3.4943

Max Act: 3.1200. Min Act: -0.0000

Data Index: 306024 (The Pile)

Max Activating Token Index: 463

Text #9

Max Range: 3.4943. Min Range: -3.4943

Max Act: 2.9493. Min Act: -0.0000

Data Index: 749644 (The Pile)

Max Activating Token Index: 344

Text #10

Max Range: 3.4943. Min Range: -3.4943

Max Act: 3.0432. Min Act: -0.0000

Data Index: 1240741 (The Pile)

Max Activating Token Index: 1002

Text #11

Max Range: 3.4943. Min Range: -3.4943

Max Act: 2.8917. Min Act: -0.0000

Data Index: 109817 (The Pile)

Max Activating Token Index: 111

Text #12

Max Range: 3.4943. Min Range: -3.4943

Max Act: 2.6000. Min Act: -0.0000

Data Index: 1353192 (The Pile)

Max Activating Token Index: 877

Text #13

Max Range: 3.4943. Min Range: -3.4943

Max Act: 2.9978. Min Act: -0.0000

Data Index: 447694 (The Pile)

Max Activating Token Index: 563

Text #14

Max Range: 3.4943. Min Range: -3.4943

Max Act: 3.0050. Min Act: -0.0000

Data Index: 1560186 (The Pile)

Max Activating Token Index: 1016

Text #15

Max Range: 3.4943. Min Range: -3.4943

Max Act: 2.8549. Min Act: -0.0000

Data Index: 936032 (The Pile)

Max Activating Token Index: 1003

Text #16

Max Range: 3.4943. Min Range: -3.4943

Max Act: 2.6854. Min Act: -0.0000

Data Index: 1717036 (The Pile)

Max Activating Token Index: 780

Text #17

Max Range: 3.4943. Min Range: -3.4943

Max Act: 2.8003. Min Act: -0.0000

Data Index: 1091279 (The Pile)

Max Activating Token Index: 813

Text #18

Max Range: 3.4943. Min Range: -3.4943

Max Act: 2.6637. Min Act: -0.0000

Data Index: 1985781 (The Pile)

Max Activating Token Index: 103

Text #19

Max Range: 3.4943. Min Range: -3.4943

Max Act: 3.0411. Min Act: -0.0000

Data Index: 1427958 (The Pile)

Max Activating Token Index: 683