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

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

Neuron 834 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6108. Min Range: -1.6108

Max Act: 1.6108. Min Act: -0.0001

Data Index: 1315187 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 1.6108. Min Range: -1.6108

Max Act: 1.5529. Min Act: -0.0001

Data Index: 354292 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 1.6108. Min Range: -1.6108

Max Act: 1.4852. Min Act: -0.0001

Data Index: 1244170 (C4 (Web Text))

Max Activating Token Index: 713

Text #3

Max Range: 1.6108. Min Range: -1.6108

Max Act: 1.5099. Min Act: -0.0001

Data Index: 1281249 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 1.6108. Min Range: -1.6108

Max Act: 1.5115. Min Act: -0.0001

Data Index: 1054844 (C4 (Web Text))

Max Activating Token Index: 397

Text #5

Max Range: 1.6108. Min Range: -1.6108

Max Act: 1.3702. Min Act: -0.0001

Data Index: 469599 (C4 (Web Text))

Max Activating Token Index: 327

Text #6

Max Range: 1.6108. Min Range: -1.6108

Max Act: 1.4257. Min Act: -0.0001

Data Index: 163991 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 1.6108. Min Range: -1.6108

Max Act: 1.3328. Min Act: -0.0001

Data Index: 1097792 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 1.6108. Min Range: -1.6108

Max Act: 1.4108. Min Act: -0.0001

Data Index: 237852 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 1.6108. Min Range: -1.6108

Max Act: 1.3728. Min Act: -0.0001

Data Index: 203431 (C4 (Web Text))

Max Activating Token Index: 687

Text #10

Max Range: 1.6108. Min Range: -1.6108

Max Act: 1.3771. Min Act: -0.0001

Data Index: 267382 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 1.6108. Min Range: -1.6108

Max Act: 1.4401. Min Act: -0.0001

Data Index: 36004 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 1.6108. Min Range: -1.6108

Max Act: 1.4010. Min Act: -0.0001

Data Index: 1237633 (C4 (Web Text))

Max Activating Token Index: 231

Text #13

Max Range: 1.6108. Min Range: -1.6108

Max Act: 1.3512. Min Act: -0.0001

Data Index: 391483 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 1.6108. Min Range: -1.6108

Max Act: 1.3906. Min Act: -0.0001

Data Index: 1172476 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 1.6108. Min Range: -1.6108

Max Act: 1.3427. Min Act: -0.0001

Data Index: 211306 (C4 (Web Text))

Max Activating Token Index: 528

Text #16

Max Range: 1.6108. Min Range: -1.6108

Max Act: 1.3934. Min Act: -0.0001

Data Index: 396220 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 1.6108. Min Range: -1.6108

Max Act: 1.2877. Min Act: -0.0001

Data Index: 344400 (C4 (Web Text))

Max Activating Token Index: 534

Text #18

Max Range: 1.6108. Min Range: -1.6108

Max Act: 1.3706. Min Act: -0.0001

Data Index: 515284 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 1.6108. Min Range: -1.6108

Max Act: 1.3989. Min Act: -0.0001

Data Index: 1337262 (C4 (Web Text))

Max Activating Token Index: 912