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

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

Neuron 1402 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0234. Min Range: -4.0234

Max Act: 3.8702. Min Act: -0.0000

Data Index: 308174 (C4 (Web Text))

Max Activating Token Index: 336

Text #1

Max Range: 4.0234. Min Range: -4.0234

Max Act: 3.6938. Min Act: -0.0000

Data Index: 1014776 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 4.0234. Min Range: -4.0234

Max Act: 3.6636. Min Act: -0.0000

Data Index: 251939 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 4.0234. Min Range: -4.0234

Max Act: 4.0234. Min Act: -0.0001

Data Index: 29502 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 4.0234. Min Range: -4.0234

Max Act: 3.4406. Min Act: -0.0000

Data Index: 1196833 (C4 (Web Text))

Max Activating Token Index: 289

Text #5

Max Range: 4.0234. Min Range: -4.0234

Max Act: 3.6773. Min Act: -0.0000

Data Index: 369940 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 4.0234. Min Range: -4.0234

Max Act: 3.4498. Min Act: -0.0000

Data Index: 794023 (C4 (Web Text))

Max Activating Token Index: 1013

Text #7

Max Range: 4.0234. Min Range: -4.0234

Max Act: 3.0260. Min Act: -0.0000

Data Index: 1242973 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 4.0234. Min Range: -4.0234

Max Act: 2.8172. Min Act: -0.0000

Data Index: 647867 (C4 (Web Text))

Max Activating Token Index: 901

Text #9

Max Range: 4.0234. Min Range: -4.0234

Max Act: 2.8727. Min Act: -0.0000

Data Index: 1245309 (C4 (Web Text))

Max Activating Token Index: 719

Text #10

Max Range: 4.0234. Min Range: -4.0234

Max Act: 2.7004. Min Act: -0.0000

Data Index: 645893 (C4 (Web Text))

Max Activating Token Index: 933

Text #11

Max Range: 4.0234. Min Range: -4.0234

Max Act: 2.7033. Min Act: -0.0000

Data Index: 1328231 (C4 (Web Text))

Max Activating Token Index: 539

Text #12

Max Range: 4.0234. Min Range: -4.0234

Max Act: 2.8202. Min Act: -0.0000

Data Index: 36072 (C4 (Web Text))

Max Activating Token Index: 592

Text #13

Max Range: 4.0234. Min Range: -4.0234

Max Act: 2.8251. Min Act: -0.0000

Data Index: 621281 (C4 (Web Text))

Max Activating Token Index: 433

Text #14

Max Range: 4.0234. Min Range: -4.0234

Max Act: 2.7562. Min Act: -0.0000

Data Index: 223173 (C4 (Web Text))

Max Activating Token Index: 803

Text #15

Max Range: 4.0234. Min Range: -4.0234

Max Act: 2.7210. Min Act: -0.0000

Data Index: 989438 (C4 (Web Text))

Max Activating Token Index: 759

Text #16

Max Range: 4.0234. Min Range: -4.0234

Max Act: 2.7316. Min Act: -0.0000

Data Index: 1063286 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 4.0234. Min Range: -4.0234

Max Act: 2.7011. Min Act: -0.0000

Data Index: 13016 (C4 (Web Text))

Max Activating Token Index: 546

Text #18

Max Range: 4.0234. Min Range: -4.0234

Max Act: 2.7101. Min Act: -0.0000

Data Index: 473810 (C4 (Web Text))

Max Activating Token Index: 40

Text #19

Max Range: 4.0234. Min Range: -4.0234

Max Act: 2.6506. Min Act: -0.0000

Data Index: 643335 (C4 (Web Text))

Max Activating Token Index: 505