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

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

Neuron 913 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6895. Min Range: -1.6895

Max Act: 1.6895. Min Act: -0.0000

Data Index: 492658 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 1.6895. Min Range: -1.6895

Max Act: 1.1722. Min Act: -0.0000

Data Index: 1109847 (C4 (Web Text))

Max Activating Token Index: 259

Text #2

Max Range: 1.6895. Min Range: -1.6895

Max Act: 1.2645. Min Act: -0.0000

Data Index: 1082792 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 1.6895. Min Range: -1.6895

Max Act: 1.2211. Min Act: -0.0000

Data Index: 859360 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 1.6895. Min Range: -1.6895

Max Act: 1.2886. Min Act: -0.0000

Data Index: 582297 (C4 (Web Text))

Max Activating Token Index: 176

Text #5

Max Range: 1.6895. Min Range: -1.6895

Max Act: 1.2073. Min Act: -0.0000

Data Index: 253041 (C4 (Web Text))

Max Activating Token Index: 185

Text #6

Max Range: 1.6895. Min Range: -1.6895

Max Act: 1.1362. Min Act: -0.0000

Data Index: 295300 (C4 (Web Text))

Max Activating Token Index: 884

Text #7

Max Range: 1.6895. Min Range: -1.6895

Max Act: 1.2109. Min Act: -0.0000

Data Index: 1276585 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 1.6895. Min Range: -1.6895

Max Act: 1.1552. Min Act: -0.0000

Data Index: 97414 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 1.6895. Min Range: -1.6895

Max Act: 1.2069. Min Act: -0.0000

Data Index: 58112 (C4 (Web Text))

Max Activating Token Index: 840

Text #10

Max Range: 1.6895. Min Range: -1.6895

Max Act: 1.1230. Min Act: -0.0000

Data Index: 190574 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 1.6895. Min Range: -1.6895

Max Act: 1.1188. Min Act: -0.0000

Data Index: 448178 (C4 (Web Text))

Max Activating Token Index: 722

Text #12

Max Range: 1.6895. Min Range: -1.6895

Max Act: 1.1164. Min Act: -0.0000

Data Index: 116700 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 1.6895. Min Range: -1.6895

Max Act: 1.1860. Min Act: -0.0000

Data Index: 1004571 (C4 (Web Text))

Max Activating Token Index: 95

Text #14

Max Range: 1.6895. Min Range: -1.6895

Max Act: 1.1340. Min Act: -0.0000

Data Index: 140872 (C4 (Web Text))

Max Activating Token Index: 330

Text #15

Max Range: 1.6895. Min Range: -1.6895

Max Act: 1.0742. Min Act: -0.0000

Data Index: 656239 (C4 (Web Text))

Max Activating Token Index: 638

Text #16

Max Range: 1.6895. Min Range: -1.6895

Max Act: 1.1406. Min Act: -0.0000

Data Index: 147749 (C4 (Web Text))

Max Activating Token Index: 281

Text #17

Max Range: 1.6895. Min Range: -1.6895

Max Act: 1.1732. Min Act: -0.0000

Data Index: 5488 (C4 (Web Text))

Max Activating Token Index: 282

Text #18

Max Range: 1.6895. Min Range: -1.6895

Max Act: 1.1041. Min Act: -0.0000

Data Index: 686520 (C4 (Web Text))

Max Activating Token Index: 76

Text #19

Max Range: 1.6895. Min Range: -1.6895

Max Act: 1.0906. Min Act: -0.0000

Data Index: 538625 (C4 (Web Text))

Max Activating Token Index: 210