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

Dataset: The Pile

Neuron 3481 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9558. Min Range: -1.9558

Max Act: 1.9558. Min Act: -0.0000

Data Index: 1360932 (The Pile)

Max Activating Token Index: 930

Text #1

Max Range: 1.9558. Min Range: -1.9558

Max Act: 1.5204. Min Act: -0.0000

Data Index: 43193 (The Pile)

Max Activating Token Index: 615

Text #2

Max Range: 1.9558. Min Range: -1.9558

Max Act: 1.4621. Min Act: -0.0000

Data Index: 584934 (The Pile)

Max Activating Token Index: 699

Text #3

Max Range: 1.9558. Min Range: -1.9558

Max Act: 1.4217. Min Act: -0.0000

Data Index: 1361169 (The Pile)

Max Activating Token Index: 687

Text #4

Max Range: 1.9558. Min Range: -1.9558

Max Act: 1.4164. Min Act: -0.0000

Data Index: 1203224 (The Pile)

Max Activating Token Index: 640

Text #5

Max Range: 1.9558. Min Range: -1.9558

Max Act: 1.1537. Min Act: -0.0000

Data Index: 1240230 (The Pile)

Max Activating Token Index: 541

Text #6

Max Range: 1.9558. Min Range: -1.9558

Max Act: 1.3549. Min Act: -0.0000

Data Index: 704297 (The Pile)

Max Activating Token Index: 649

Text #7

Max Range: 1.9558. Min Range: -1.9558

Max Act: 1.5145. Min Act: -0.0000

Data Index: 1871750 (The Pile)

Max Activating Token Index: 143

Text #8

Max Range: 1.9558. Min Range: -1.9558

Max Act: 1.2300. Min Act: 0.0000

Data Index: 756207 (The Pile)

Max Activating Token Index: 245

Text #9

Max Range: 1.9558. Min Range: -1.9558

Max Act: 1.2705. Min Act: 0.0000

Data Index: 16739 (The Pile)

Max Activating Token Index: 181

Text #10

Max Range: 1.9558. Min Range: -1.9558

Max Act: 1.1198. Min Act: 0.0000

Data Index: 1634039 (The Pile)

Max Activating Token Index: 46

Text #11

Max Range: 1.9558. Min Range: -1.9558

Max Act: 1.2711. Min Act: -0.0000

Data Index: 1492366 (The Pile)

Max Activating Token Index: 254

Text #12

Max Range: 1.9558. Min Range: -1.9558

Max Act: 1.1948. Min Act: -0.0000

Data Index: 1403013 (The Pile)

Max Activating Token Index: 662

Text #13

Max Range: 1.9558. Min Range: -1.9558

Max Act: 1.1647. Min Act: -0.0000

Data Index: 1077661 (The Pile)

Max Activating Token Index: 404

Text #14

Max Range: 1.9558. Min Range: -1.9558

Max Act: 1.2609. Min Act: 0.0000

Data Index: 529515 (The Pile)

Max Activating Token Index: 735

Text #15

Max Range: 1.9558. Min Range: -1.9558

Max Act: 1.1516. Min Act: -0.0000

Data Index: 1416936 (The Pile)

Max Activating Token Index: 158

Text #16

Max Range: 1.9558. Min Range: -1.9558

Max Act: 1.5065. Min Act: -0.0000

Data Index: 642195 (The Pile)

Max Activating Token Index: 1007

Text #17

Max Range: 1.9558. Min Range: -1.9558

Max Act: 1.2489. Min Act: -0.0000

Data Index: 1139576 (The Pile)

Max Activating Token Index: 285

Text #18

Max Range: 1.9558. Min Range: -1.9558

Max Act: 1.2117. Min Act: 0.0000

Data Index: 876964 (The Pile)

Max Activating Token Index: 183

Text #19

Max Range: 1.9558. Min Range: -1.9558

Max Act: 1.3207. Min Act: -0.0000

Data Index: 474097 (The Pile)

Max Activating Token Index: 930