Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3015 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5572. Min Range: -1.5572

Max Act: 1.5572. Min Act: -0.0000

Data Index: 614099 (C4 (Web Text))

Max Activating Token Index: 887

Text #1

Max Range: 1.5572. Min Range: -1.5572

Max Act: 1.5014. Min Act: -0.0000

Data Index: 93672 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 1.5572. Min Range: -1.5572

Max Act: 1.2037. Min Act: -0.0000

Data Index: 1032082 (C4 (Web Text))

Max Activating Token Index: 51

Text #3

Max Range: 1.5572. Min Range: -1.5572

Max Act: 1.2491. Min Act: -0.0000

Data Index: 104284 (C4 (Web Text))

Max Activating Token Index: 840

Text #4

Max Range: 1.5572. Min Range: -1.5572

Max Act: 1.1596. Min Act: -0.0000

Data Index: 907263 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 1.5572. Min Range: -1.5572

Max Act: 1.0992. Min Act: -0.0000

Data Index: 549 (C4 (Web Text))

Max Activating Token Index: 101

Text #6

Max Range: 1.5572. Min Range: -1.5572

Max Act: 1.1270. Min Act: -0.0000

Data Index: 948375 (C4 (Web Text))

Max Activating Token Index: 287

Text #7

Max Range: 1.5572. Min Range: -1.5572

Max Act: 1.2471. Min Act: -0.0000

Data Index: 1008364 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 1.5572. Min Range: -1.5572

Max Act: 1.1214. Min Act: -0.0000

Data Index: 622823 (C4 (Web Text))

Max Activating Token Index: 595

Text #9

Max Range: 1.5572. Min Range: -1.5572

Max Act: 1.1200. Min Act: -0.0000

Data Index: 236803 (C4 (Web Text))

Max Activating Token Index: 1021

Text #10

Max Range: 1.5572. Min Range: -1.5572

Max Act: 1.0860. Min Act: -0.0000

Data Index: 412268 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 1.5572. Min Range: -1.5572

Max Act: 1.1159. Min Act: -0.0001

Data Index: 750633 (C4 (Web Text))

Max Activating Token Index: 623

Text #12

Max Range: 1.5572. Min Range: -1.5572

Max Act: 1.0634. Min Act: -0.0000

Data Index: 507496 (C4 (Web Text))

Max Activating Token Index: 691

Text #13

Max Range: 1.5572. Min Range: -1.5572

Max Act: 1.1645. Min Act: -0.0000

Data Index: 216007 (C4 (Web Text))

Max Activating Token Index: 882

Text #14

Max Range: 1.5572. Min Range: -1.5572

Max Act: 1.0828. Min Act: -0.0000

Data Index: 610701 (C4 (Web Text))

Max Activating Token Index: 929

Text #15

Max Range: 1.5572. Min Range: -1.5572

Max Act: 0.9772. Min Act: -0.0000

Data Index: 360703 (C4 (Web Text))

Max Activating Token Index: 395

Text #16

Max Range: 1.5572. Min Range: -1.5572

Max Act: 1.0138. Min Act: -0.0000

Data Index: 693792 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 1.5572. Min Range: -1.5572

Max Act: 1.0704. Min Act: -0.0000

Data Index: 1108125 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 1.5572. Min Range: -1.5572

Max Act: 1.0498. Min Act: -0.0000

Data Index: 482405 (C4 (Web Text))

Max Activating Token Index: 1010

Text #19

Max Range: 1.5572. Min Range: -1.5572

Max Act: 0.9526. Min Act: -0.0000

Data Index: 1480181 (Python Code)

Max Activating Token Index: 118