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

Dataset: The Pile

Neuron 1674 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6672. Min Range: -3.6672

Max Act: 3.6672. Min Act: -0.0000

Data Index: 576422 (The Pile)

Max Activating Token Index: 293

Text #1

Max Range: 3.6672. Min Range: -3.6672

Max Act: 3.5362. Min Act: -0.0000

Data Index: 330752 (The Pile)

Max Activating Token Index: 735

Text #2

Max Range: 3.6672. Min Range: -3.6672

Max Act: 3.1512. Min Act: -0.0000

Data Index: 592952 (The Pile)

Max Activating Token Index: 109

Text #3

Max Range: 3.6672. Min Range: -3.6672

Max Act: 2.8707. Min Act: -0.0000

Data Index: 736316 (The Pile)

Max Activating Token Index: 113

Text #4

Max Range: 3.6672. Min Range: -3.6672

Max Act: 2.7938. Min Act: -0.0000

Data Index: 1139653 (The Pile)

Max Activating Token Index: 855

Text #5

Max Range: 3.6672. Min Range: -3.6672

Max Act: 2.6051. Min Act: -0.0000

Data Index: 1993527 (The Pile)

Max Activating Token Index: 870

Text #6

Max Range: 3.6672. Min Range: -3.6672

Max Act: 2.6214. Min Act: -0.0000

Data Index: 1825873 (The Pile)

Max Activating Token Index: 408

Text #7

Max Range: 3.6672. Min Range: -3.6672

Max Act: 2.7815. Min Act: -0.0000

Data Index: 573257 (The Pile)

Max Activating Token Index: 206

Text #8

Max Range: 3.6672. Min Range: -3.6672

Max Act: 2.8730. Min Act: -0.0000

Data Index: 1504759 (The Pile)

Max Activating Token Index: 844

Text #9

Max Range: 3.6672. Min Range: -3.6672

Max Act: 2.5836. Min Act: -0.0000

Data Index: 87095 (The Pile)

Max Activating Token Index: 209

Text #10

Max Range: 3.6672. Min Range: -3.6672

Max Act: 2.6469. Min Act: -0.0000

Data Index: 583662 (The Pile)

Max Activating Token Index: 214

Text #11

Max Range: 3.6672. Min Range: -3.6672

Max Act: 2.7112. Min Act: -0.0000

Data Index: 1303580 (The Pile)

Max Activating Token Index: 450

Text #12

Max Range: 3.6672. Min Range: -3.6672

Max Act: 2.5771. Min Act: -0.0000

Data Index: 1850706 (The Pile)

Max Activating Token Index: 466

Text #13

Max Range: 3.6672. Min Range: -3.6672

Max Act: 2.4011. Min Act: -0.0000

Data Index: 1667921 (The Pile)

Max Activating Token Index: 48

Text #14

Max Range: 3.6672. Min Range: -3.6672

Max Act: 2.3921. Min Act: -0.0000

Data Index: 192474 (The Pile)

Max Activating Token Index: 376

Text #15

Max Range: 3.6672. Min Range: -3.6672

Max Act: 2.2679. Min Act: -0.0000

Data Index: 1190987 (The Pile)

Max Activating Token Index: 219

Text #16

Max Range: 3.6672. Min Range: -3.6672

Max Act: 2.4629. Min Act: -0.0000

Data Index: 1843427 (The Pile)

Max Activating Token Index: 315

Text #17

Max Range: 3.6672. Min Range: -3.6672

Max Act: 2.3303. Min Act: -0.0000

Data Index: 1094186 (The Pile)

Max Activating Token Index: 440

Text #18

Max Range: 3.6672. Min Range: -3.6672

Max Act: 2.4177. Min Act: -0.0000

Data Index: 1161169 (The Pile)

Max Activating Token Index: 180

Text #19

Max Range: 3.6672. Min Range: -3.6672

Max Act: 2.2741. Min Act: -0.0000

Data Index: 1310604 (The Pile)

Max Activating Token Index: 360