Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1629 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.5168. Min Range: -1.5168

Max Act: 1.5168. Min Act: -0.0000

Data Index: 1203917 (The Pile)

Max Activating Token Index: 565

Text #1

Max Range: 1.5168. Min Range: -1.5168

Max Act: 1.1116. Min Act: -0.0000

Data Index: 421035 (The Pile)

Max Activating Token Index: 973

Text #2

Max Range: 1.5168. Min Range: -1.5168

Max Act: 1.1082. Min Act: -0.0000

Data Index: 1969088 (The Pile)

Max Activating Token Index: 8

Text #3

Max Range: 1.5168. Min Range: -1.5168

Max Act: 1.0825. Min Act: -0.0000

Data Index: 127628 (The Pile)

Max Activating Token Index: 348

Text #4

Max Range: 1.5168. Min Range: -1.5168

Max Act: 1.0507. Min Act: -0.0000

Data Index: 1013879 (The Pile)

Max Activating Token Index: 691

Text #5

Max Range: 1.5168. Min Range: -1.5168

Max Act: 1.0308. Min Act: -0.0000

Data Index: 662685 (The Pile)

Max Activating Token Index: 752

Text #6

Max Range: 1.5168. Min Range: -1.5168

Max Act: 1.0207. Min Act: -0.0000

Data Index: 1937380 (The Pile)

Max Activating Token Index: 411

Text #7

Max Range: 1.5168. Min Range: -1.5168

Max Act: 1.0182. Min Act: -0.0000

Data Index: 1006095 (The Pile)

Max Activating Token Index: 47

Text #8

Max Range: 1.5168. Min Range: -1.5168

Max Act: 1.1007. Min Act: -0.0000

Data Index: 1300543 (The Pile)

Max Activating Token Index: 652

Text #9

Max Range: 1.5168. Min Range: -1.5168

Max Act: 0.9997. Min Act: -0.0000

Data Index: 720310 (The Pile)

Max Activating Token Index: 197

Text #10

Max Range: 1.5168. Min Range: -1.5168

Max Act: 1.0259. Min Act: -0.0000

Data Index: 1108020 (The Pile)

Max Activating Token Index: 786

Text #11

Max Range: 1.5168. Min Range: -1.5168

Max Act: 1.0274. Min Act: -0.0000

Data Index: 1464746 (The Pile)

Max Activating Token Index: 861

Text #12

Max Range: 1.5168. Min Range: -1.5168

Max Act: 0.9791. Min Act: -0.0000

Data Index: 1837071 (The Pile)

Max Activating Token Index: 278

Text #13

Max Range: 1.5168. Min Range: -1.5168

Max Act: 1.0025. Min Act: -0.0000

Data Index: 743462 (The Pile)

Max Activating Token Index: 784

Text #14

Max Range: 1.5168. Min Range: -1.5168

Max Act: 1.0587. Min Act: -0.0000

Data Index: 1794255 (The Pile)

Max Activating Token Index: 569

Text #15

Max Range: 1.5168. Min Range: -1.5168

Max Act: 0.9725. Min Act: -0.0000

Data Index: 1252009 (The Pile)

Max Activating Token Index: 522

Text #16

Max Range: 1.5168. Min Range: -1.5168

Max Act: 0.9928. Min Act: -0.0000

Data Index: 837819 (The Pile)

Max Activating Token Index: 824

Text #17

Max Range: 1.5168. Min Range: -1.5168

Max Act: 0.9861. Min Act: -0.0000

Data Index: 160414 (The Pile)

Max Activating Token Index: 110

Text #18

Max Range: 1.5168. Min Range: -1.5168

Max Act: 1.0023. Min Act: -0.0000

Data Index: 1946566 (The Pile)

Max Activating Token Index: 705

Text #19

Max Range: 1.5168. Min Range: -1.5168

Max Act: 0.9916. Min Act: -0.0000

Data Index: 71348 (The Pile)

Max Activating Token Index: 791