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

Dataset: The Pile

Neuron 2868 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.8066. Min Act: -0.0000

Data Index: 1747179 (The Pile)

Max Activating Token Index: 183

Text #1

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.7695. Min Act: -0.0000

Data Index: 1271656 (The Pile)

Max Activating Token Index: 341

Text #2

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.7249. Min Act: -0.0000

Data Index: 164876 (The Pile)

Max Activating Token Index: 597

Text #3

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.7610. Min Act: -0.0000

Data Index: 1182356 (The Pile)

Max Activating Token Index: 482

Text #4

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.6486. Min Act: -0.0000

Data Index: 549450 (The Pile)

Max Activating Token Index: 976

Text #5

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.7497. Min Act: -0.0000

Data Index: 1803264 (The Pile)

Max Activating Token Index: 177

Text #6

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.7438. Min Act: -0.0000

Data Index: 1405479 (The Pile)

Max Activating Token Index: 655

Text #7

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.6303. Min Act: -0.0000

Data Index: 1004376 (The Pile)

Max Activating Token Index: 793

Text #8

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.6912. Min Act: -0.0000

Data Index: 83488 (The Pile)

Max Activating Token Index: 137

Text #9

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.6650. Min Act: -0.0000

Data Index: 470756 (The Pile)

Max Activating Token Index: 725

Text #10

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.7035. Min Act: -0.0000

Data Index: 1580634 (The Pile)

Max Activating Token Index: 899

Text #11

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.5556. Min Act: -0.0000

Data Index: 1946634 (The Pile)

Max Activating Token Index: 664

Text #12

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.6664. Min Act: -0.0000

Data Index: 1761157 (The Pile)

Max Activating Token Index: 962

Text #13

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.6534. Min Act: -0.0000

Data Index: 1746083 (The Pile)

Max Activating Token Index: 769

Text #14

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.6139. Min Act: -0.0000

Data Index: 496055 (The Pile)

Max Activating Token Index: 246

Text #15

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.6715. Min Act: -0.0000

Data Index: 1976354 (The Pile)

Max Activating Token Index: 102

Text #16

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.6177. Min Act: -0.0000

Data Index: 667144 (The Pile)

Max Activating Token Index: 46

Text #17

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.6359. Min Act: -0.0000

Data Index: 792975 (The Pile)

Max Activating Token Index: 91

Text #18

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.6662. Min Act: -0.0000

Data Index: 1384886 (The Pile)

Max Activating Token Index: 808

Text #19

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.6258. Min Act: -0.0000

Data Index: 733637 (The Pile)

Max Activating Token Index: 490