Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 329 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1345. Min Act: -0.0003

Data Index: 382867 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1341. Min Act: -0.0003

Data Index: 773569 (C4 (Web Text))

Max Activating Token Index: 459

Text #2

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1247. Min Act: -0.0003

Data Index: 783312 (C4 (Web Text))

Max Activating Token Index: 699

Text #3

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1244. Min Act: -0.0003

Data Index: 1201263 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1163. Min Act: -0.0003

Data Index: 264581 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1138. Min Act: -0.0003

Data Index: 1025288 (C4 (Web Text))

Max Activating Token Index: 412

Text #6

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1229. Min Act: -0.0003

Data Index: 579913 (C4 (Web Text))

Max Activating Token Index: 287

Text #7

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1056. Min Act: -0.0003

Data Index: 386935 (C4 (Web Text))

Max Activating Token Index: 326

Text #8

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0987. Min Act: -0.0003

Data Index: 181476 (C4 (Web Text))

Max Activating Token Index: 836

Text #9

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1007. Min Act: -0.0003

Data Index: 906371 (C4 (Web Text))

Max Activating Token Index: 690

Text #10

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0979. Min Act: -0.0003

Data Index: 699520 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1049. Min Act: -0.0003

Data Index: 949185 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0936. Min Act: -0.0003

Data Index: 1092000 (C4 (Web Text))

Max Activating Token Index: 391

Text #13

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0981. Min Act: -0.0003

Data Index: 600333 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0962. Min Act: -0.0003

Data Index: 73491 (C4 (Web Text))

Max Activating Token Index: 416

Text #15

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0891. Min Act: -0.0003

Data Index: 1355681 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0899. Min Act: -0.0003

Data Index: 485032 (C4 (Web Text))

Max Activating Token Index: 917

Text #17

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0945. Min Act: -0.0003

Data Index: 916504 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0972. Min Act: -0.0003

Data Index: 1137826 (C4 (Web Text))

Max Activating Token Index: 778

Text #19

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0929. Min Act: -0.0003

Data Index: 377009 (C4 (Web Text))

Max Activating Token Index: 201