Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 820 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7579. Min Range: -1.7579

Max Act: 1.7579. Min Act: -0.0001

Data Index: 484730 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 1.7579. Min Range: -1.7579

Max Act: 1.6851. Min Act: -0.0001

Data Index: 281769 (C4 (Web Text))

Max Activating Token Index: 937

Text #2

Max Range: 1.7579. Min Range: -1.7579

Max Act: 1.6761. Min Act: -0.0000

Data Index: 140618 (C4 (Web Text))

Max Activating Token Index: 301

Text #3

Max Range: 1.7579. Min Range: -1.7579

Max Act: 1.5384. Min Act: -0.0001

Data Index: 941761 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 1.7579. Min Range: -1.7579

Max Act: 1.4912. Min Act: -0.0001

Data Index: 393356 (C4 (Web Text))

Max Activating Token Index: 673

Text #5

Max Range: 1.7579. Min Range: -1.7579

Max Act: 1.6068. Min Act: -0.0001

Data Index: 403192 (C4 (Web Text))

Max Activating Token Index: 32

Text #6

Max Range: 1.7579. Min Range: -1.7579

Max Act: 1.4593. Min Act: -0.0001

Data Index: 110480 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 1.7579. Min Range: -1.7579

Max Act: 1.4503. Min Act: -0.0001

Data Index: 612528 (C4 (Web Text))

Max Activating Token Index: 359

Text #8

Max Range: 1.7579. Min Range: -1.7579

Max Act: 1.5354. Min Act: -0.0001

Data Index: 1231903 (C4 (Web Text))

Max Activating Token Index: 349

Text #9

Max Range: 1.7579. Min Range: -1.7579

Max Act: 1.4037. Min Act: -0.0001

Data Index: 1036521 (C4 (Web Text))

Max Activating Token Index: 136

Text #10

Max Range: 1.7579. Min Range: -1.7579

Max Act: 1.3896. Min Act: -0.0000

Data Index: 1027272 (C4 (Web Text))

Max Activating Token Index: 91

Text #11

Max Range: 1.7579. Min Range: -1.7579

Max Act: 1.4125. Min Act: -0.0001

Data Index: 330560 (C4 (Web Text))

Max Activating Token Index: 691

Text #12

Max Range: 1.7579. Min Range: -1.7579

Max Act: 1.4471. Min Act: -0.0000

Data Index: 40242 (C4 (Web Text))

Max Activating Token Index: 359

Text #13

Max Range: 1.7579. Min Range: -1.7579

Max Act: 1.3211. Min Act: -0.0001

Data Index: 646352 (C4 (Web Text))

Max Activating Token Index: 83

Text #14

Max Range: 1.7579. Min Range: -1.7579

Max Act: 1.3188. Min Act: -0.0001

Data Index: 1254576 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 1.7579. Min Range: -1.7579

Max Act: 1.2472. Min Act: -0.0001

Data Index: 1337149 (C4 (Web Text))

Max Activating Token Index: 685

Text #16

Max Range: 1.7579. Min Range: -1.7579

Max Act: 1.2852. Min Act: -0.0001

Data Index: 426988 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 1.7579. Min Range: -1.7579

Max Act: 1.2733. Min Act: -0.0001

Data Index: 1270355 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 1.7579. Min Range: -1.7579

Max Act: 1.3291. Min Act: -0.0001

Data Index: 107126 (C4 (Web Text))

Max Activating Token Index: 494

Text #19

Max Range: 1.7579. Min Range: -1.7579

Max Act: 1.3619. Min Act: -0.0001

Data Index: 515074 (C4 (Web Text))

Max Activating Token Index: 633