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

Dataset: The Pile

Neuron 532 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0171. Min Range: -1.0171

Max Act: 1.0171. Min Act: -0.0000

Data Index: 1237507 (The Pile)

Max Activating Token Index: 90

Text #1

Max Range: 1.0171. Min Range: -1.0171

Max Act: 0.7599. Min Act: -0.0000

Data Index: 1153495 (The Pile)

Max Activating Token Index: 316

Text #2

Max Range: 1.0171. Min Range: -1.0171

Max Act: 0.7722. Min Act: -0.0000

Data Index: 1465319 (The Pile)

Max Activating Token Index: 32

Text #3

Max Range: 1.0171. Min Range: -1.0171

Max Act: 0.7421. Min Act: -0.0000

Data Index: 104326 (The Pile)

Max Activating Token Index: 112

Text #4

Max Range: 1.0171. Min Range: -1.0171

Max Act: 0.7531. Min Act: -0.0000

Data Index: 1292677 (The Pile)

Max Activating Token Index: 412

Text #5

Max Range: 1.0171. Min Range: -1.0171

Max Act: 0.6884. Min Act: -0.0000

Data Index: 223836 (The Pile)

Max Activating Token Index: 39

Text #6

Max Range: 1.0171. Min Range: -1.0171

Max Act: 0.6590. Min Act: -0.0000

Data Index: 715539 (The Pile)

Max Activating Token Index: 111

Text #7

Max Range: 1.0171. Min Range: -1.0171

Max Act: 0.7041. Min Act: -0.0000

Data Index: 305620 (The Pile)

Max Activating Token Index: 213

Text #8

Max Range: 1.0171. Min Range: -1.0171

Max Act: 0.7180. Min Act: -0.0000

Data Index: 821434 (The Pile)

Max Activating Token Index: 116

Text #9

Max Range: 1.0171. Min Range: -1.0171

Max Act: 0.6724. Min Act: -0.0000

Data Index: 354405 (The Pile)

Max Activating Token Index: 942

Text #10

Max Range: 1.0171. Min Range: -1.0171

Max Act: 0.7078. Min Act: -0.0000

Data Index: 32677 (The Pile)

Max Activating Token Index: 47

Text #11

Max Range: 1.0171. Min Range: -1.0171

Max Act: 0.6321. Min Act: -0.0000

Data Index: 1158614 (The Pile)

Max Activating Token Index: 197

Text #12

Max Range: 1.0171. Min Range: -1.0171

Max Act: 0.7046. Min Act: -0.0000

Data Index: 154571 (The Pile)

Max Activating Token Index: 113

Text #13

Max Range: 1.0171. Min Range: -1.0171

Max Act: 0.6260. Min Act: -0.0000

Data Index: 751222 (The Pile)

Max Activating Token Index: 520

Text #14

Max Range: 1.0171. Min Range: -1.0171

Max Act: 0.6510. Min Act: -0.0000

Data Index: 233991 (The Pile)

Max Activating Token Index: 94

Text #15

Max Range: 1.0171. Min Range: -1.0171

Max Act: 0.6231. Min Act: -0.0000

Data Index: 1443501 (The Pile)

Max Activating Token Index: 404

Text #16

Max Range: 1.0171. Min Range: -1.0171

Max Act: 0.6439. Min Act: -0.0000

Data Index: 1231226 (The Pile)

Max Activating Token Index: 665

Text #17

Max Range: 1.0171. Min Range: -1.0171

Max Act: 0.6217. Min Act: -0.0000

Data Index: 1141494 (The Pile)

Max Activating Token Index: 715

Text #18

Max Range: 1.0171. Min Range: -1.0171

Max Act: 0.5923. Min Act: -0.0000

Data Index: 1220516 (The Pile)

Max Activating Token Index: 801

Text #19

Max Range: 1.0171. Min Range: -1.0171

Max Act: 0.6294. Min Act: -0.0000

Data Index: 520196 (The Pile)

Max Activating Token Index: 47