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

Dataset: The Pile

Neuron 1307 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: 0.6501. Min Range: -0.6501

Max Act: 0.6501. Min Act: -0.0000

Data Index: 1947491 (The Pile)

Max Activating Token Index: 929

Text #1

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.4808. Min Act: -0.0000

Data Index: 104691 (The Pile)

Max Activating Token Index: 252

Text #2

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.4517. Min Act: -0.0000

Data Index: 788662 (The Pile)

Max Activating Token Index: 197

Text #3

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.4867. Min Act: -0.0000

Data Index: 742267 (The Pile)

Max Activating Token Index: 1007

Text #4

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.4441. Min Act: -0.0000

Data Index: 635764 (The Pile)

Max Activating Token Index: 117

Text #5

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.4599. Min Act: -0.0000

Data Index: 352606 (The Pile)

Max Activating Token Index: 1013

Text #6

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.4270. Min Act: -0.0000

Data Index: 36042 (The Pile)

Max Activating Token Index: 300

Text #7

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.3949. Min Act: -0.0000

Data Index: 1828085 (The Pile)

Max Activating Token Index: 244

Text #8

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.4313. Min Act: -0.0000

Data Index: 342538 (The Pile)

Max Activating Token Index: 514

Text #9

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.3983. Min Act: -0.0000

Data Index: 608526 (The Pile)

Max Activating Token Index: 381

Text #10

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.4196. Min Act: -0.0000

Data Index: 66298 (The Pile)

Max Activating Token Index: 981

Text #11

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.3929. Min Act: -0.0000

Data Index: 1157243 (The Pile)

Max Activating Token Index: 868

Text #12

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.4125. Min Act: -0.0000

Data Index: 927174 (The Pile)

Max Activating Token Index: 162

Text #13

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.3817. Min Act: -0.0000

Data Index: 960725 (The Pile)

Max Activating Token Index: 731

Text #14

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.4134. Min Act: -0.0000

Data Index: 811793 (The Pile)

Max Activating Token Index: 886

Text #15

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.4189. Min Act: -0.0000

Data Index: 1120451 (The Pile)

Max Activating Token Index: 913

Text #16

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.3689. Min Act: -0.0000

Data Index: 905882 (The Pile)

Max Activating Token Index: 626

Text #17

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.3945. Min Act: -0.0000

Data Index: 1141245 (The Pile)

Max Activating Token Index: 163

Text #18

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.3798. Min Act: -0.0000

Data Index: 842197 (The Pile)

Max Activating Token Index: 288

Text #19

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.3724. Min Act: -0.0000

Data Index: 123513 (The Pile)

Max Activating Token Index: 981