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

Dataset: The Pile

Neuron 3530 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3792. Min Range: -1.3792

Max Act: 1.3792. Min Act: -0.0000

Data Index: 336778 (The Pile)

Max Activating Token Index: 355

Text #1

Max Range: 1.3792. Min Range: -1.3792

Max Act: 1.1784. Min Act: -0.0000

Data Index: 1855501 (The Pile)

Max Activating Token Index: 246

Text #2

Max Range: 1.3792. Min Range: -1.3792

Max Act: 1.2102. Min Act: -0.0000

Data Index: 1648533 (The Pile)

Max Activating Token Index: 154

Text #3

Max Range: 1.3792. Min Range: -1.3792

Max Act: 1.1876. Min Act: -0.0000

Data Index: 1093926 (The Pile)

Max Activating Token Index: 259

Text #4

Max Range: 1.3792. Min Range: -1.3792

Max Act: 1.0804. Min Act: -0.0000

Data Index: 408869 (The Pile)

Max Activating Token Index: 866

Text #5

Max Range: 1.3792. Min Range: -1.3792

Max Act: 1.1427. Min Act: -0.0000

Data Index: 928039 (The Pile)

Max Activating Token Index: 89

Text #6

Max Range: 1.3792. Min Range: -1.3792

Max Act: 1.0451. Min Act: -0.0000

Data Index: 24402 (The Pile)

Max Activating Token Index: 216

Text #7

Max Range: 1.3792. Min Range: -1.3792

Max Act: 1.0290. Min Act: -0.0000

Data Index: 12931 (The Pile)

Max Activating Token Index: 262

Text #8

Max Range: 1.3792. Min Range: -1.3792

Max Act: 1.0182. Min Act: -0.0000

Data Index: 1172199 (The Pile)

Max Activating Token Index: 795

Text #9

Max Range: 1.3792. Min Range: -1.3792

Max Act: 1.0768. Min Act: -0.0000

Data Index: 1103139 (The Pile)

Max Activating Token Index: 374

Text #10

Max Range: 1.3792. Min Range: -1.3792

Max Act: 1.0155. Min Act: -0.0000

Data Index: 53460 (The Pile)

Max Activating Token Index: 922

Text #11

Max Range: 1.3792. Min Range: -1.3792

Max Act: 1.1214. Min Act: -0.0000

Data Index: 1074958 (The Pile)

Max Activating Token Index: 226

Text #12

Max Range: 1.3792. Min Range: -1.3792

Max Act: 1.0646. Min Act: -0.0000

Data Index: 1768858 (The Pile)

Max Activating Token Index: 905

Text #13

Max Range: 1.3792. Min Range: -1.3792

Max Act: 1.0646. Min Act: -0.0000

Data Index: 1190961 (The Pile)

Max Activating Token Index: 77

Text #14

Max Range: 1.3792. Min Range: -1.3792

Max Act: 0.9874. Min Act: -0.0000

Data Index: 371426 (The Pile)

Max Activating Token Index: 447

Text #15

Max Range: 1.3792. Min Range: -1.3792

Max Act: 0.9952. Min Act: -0.0000

Data Index: 925197 (The Pile)

Max Activating Token Index: 196

Text #16

Max Range: 1.3792. Min Range: -1.3792

Max Act: 1.0463. Min Act: -0.0000

Data Index: 1844598 (The Pile)

Max Activating Token Index: 272

Text #17

Max Range: 1.3792. Min Range: -1.3792

Max Act: 1.1081. Min Act: -0.0000

Data Index: 702078 (The Pile)

Max Activating Token Index: 833

Text #18

Max Range: 1.3792. Min Range: -1.3792

Max Act: 1.0312. Min Act: -0.0000

Data Index: 919607 (The Pile)

Max Activating Token Index: 37

Text #19

Max Range: 1.3792. Min Range: -1.3792

Max Act: 0.9582. Min Act: -0.0000

Data Index: 231808 (The Pile)

Max Activating Token Index: 981