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

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

Neuron 4067 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1427. Min Act: -0.0001

Data Index: 1053036 (C4 (Web Text))

Max Activating Token Index: 243

Text #1

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1240. Min Act: -0.0001

Data Index: 396683 (C4 (Web Text))

Max Activating Token Index: 506

Text #2

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1233. Min Act: -0.0001

Data Index: 1032840 (C4 (Web Text))

Max Activating Token Index: 256

Text #3

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1288. Min Act: -0.0001

Data Index: 617984 (C4 (Web Text))

Max Activating Token Index: 365

Text #4

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1219. Min Act: -0.0001

Data Index: 379726 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1199. Min Act: -0.0001

Data Index: 816977 (C4 (Web Text))

Max Activating Token Index: 702

Text #6

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1081. Min Act: -0.0001

Data Index: 493183 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1163. Min Act: -0.0001

Data Index: 322919 (C4 (Web Text))

Max Activating Token Index: 514

Text #8

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1130. Min Act: -0.0001

Data Index: 423030 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1062. Min Act: -0.0001

Data Index: 229197 (C4 (Web Text))

Max Activating Token Index: 508

Text #10

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1086. Min Act: -0.0001

Data Index: 755460 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.0990. Min Act: -0.0001

Data Index: 726329 (C4 (Web Text))

Max Activating Token Index: 843

Text #12

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1022. Min Act: -0.0001

Data Index: 454535 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1021. Min Act: -0.0001

Data Index: 795568 (C4 (Web Text))

Max Activating Token Index: 437

Text #14

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1022. Min Act: -0.0001

Data Index: 638960 (C4 (Web Text))

Max Activating Token Index: 377

Text #15

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1016. Min Act: -0.0001

Data Index: 613703 (C4 (Web Text))

Max Activating Token Index: 763

Text #16

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1007. Min Act: -0.0001

Data Index: 1082016 (C4 (Web Text))

Max Activating Token Index: 1008

Text #17

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1038. Min Act: -0.0001

Data Index: 423945 (C4 (Web Text))

Max Activating Token Index: 223

Text #18

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.0934. Min Act: -0.0001

Data Index: 84980 (C4 (Web Text))

Max Activating Token Index: 64

Text #19

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1038. Min Act: -0.0001

Data Index: 46637 (C4 (Web Text))

Max Activating Token Index: 568