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

Dataset: The Pile

Neuron 3840 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1203. Min Range: -1.1203

Max Act: 1.1197. Min Act: -0.0000

Data Index: 700935 (The Pile)

Max Activating Token Index: 668

Text #1

Max Range: 1.1203. Min Range: -1.1203

Max Act: 1.1203. Min Act: -0.0000

Data Index: 745816 (The Pile)

Max Activating Token Index: 59

Text #2

Max Range: 1.1203. Min Range: -1.1203

Max Act: 1.1194. Min Act: -0.0000

Data Index: 178180 (The Pile)

Max Activating Token Index: 24

Text #3

Max Range: 1.1203. Min Range: -1.1203

Max Act: 1.0047. Min Act: -0.0000

Data Index: 27681 (The Pile)

Max Activating Token Index: 888

Text #4

Max Range: 1.1203. Min Range: -1.1203

Max Act: 0.9427. Min Act: -0.0000

Data Index: 1842245 (The Pile)

Max Activating Token Index: 62

Text #5

Max Range: 1.1203. Min Range: -1.1203

Max Act: 0.9439. Min Act: -0.0000

Data Index: 1319729 (The Pile)

Max Activating Token Index: 122

Text #6

Max Range: 1.1203. Min Range: -1.1203

Max Act: 0.8396. Min Act: -0.0000

Data Index: 1854448 (The Pile)

Max Activating Token Index: 17

Text #7

Max Range: 1.1203. Min Range: -1.1203

Max Act: 0.9671. Min Act: -0.0000

Data Index: 1848733 (The Pile)

Max Activating Token Index: 150

Text #8

Max Range: 1.1203. Min Range: -1.1203

Max Act: 0.8912. Min Act: -0.0000

Data Index: 826480 (The Pile)

Max Activating Token Index: 195

Text #9

Max Range: 1.1203. Min Range: -1.1203

Max Act: 0.8203. Min Act: -0.0000

Data Index: 1674749 (The Pile)

Max Activating Token Index: 352

Text #10

Max Range: 1.1203. Min Range: -1.1203

Max Act: 0.8590. Min Act: -0.0000

Data Index: 1315868 (The Pile)

Max Activating Token Index: 505

Text #11

Max Range: 1.1203. Min Range: -1.1203

Max Act: 0.8317. Min Act: -0.0000

Data Index: 1365812 (The Pile)

Max Activating Token Index: 407

Text #12

Max Range: 1.1203. Min Range: -1.1203

Max Act: 0.8424. Min Act: -0.0000

Data Index: 439103 (The Pile)

Max Activating Token Index: 272

Text #13

Max Range: 1.1203. Min Range: -1.1203

Max Act: 0.8642. Min Act: -0.0000

Data Index: 1001450 (The Pile)

Max Activating Token Index: 292

Text #14

Max Range: 1.1203. Min Range: -1.1203

Max Act: 0.8734. Min Act: -0.0000

Data Index: 1340404 (The Pile)

Max Activating Token Index: 44

Text #15

Max Range: 1.1203. Min Range: -1.1203

Max Act: 0.7963. Min Act: -0.0000

Data Index: 1621509 (The Pile)

Max Activating Token Index: 245

Text #16

Max Range: 1.1203. Min Range: -1.1203

Max Act: 0.7395. Min Act: -0.0000

Data Index: 1682205 (The Pile)

Max Activating Token Index: 292

Text #17

Max Range: 1.1203. Min Range: -1.1203

Max Act: 0.7488. Min Act: -0.0000

Data Index: 905081 (The Pile)

Max Activating Token Index: 82

Text #18

Max Range: 1.1203. Min Range: -1.1203

Max Act: 0.7667. Min Act: -0.0000

Data Index: 1518560 (The Pile)

Max Activating Token Index: 653

Text #19

Max Range: 1.1203. Min Range: -1.1203

Max Act: 0.7923. Min Act: -0.0000

Data Index: 1572849 (The Pile)

Max Activating Token Index: 402