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

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

Neuron 3258 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1345. Min Range: -3.1345

Max Act: 3.1345. Min Act: -0.0000

Data Index: 65032 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 3.1345. Min Range: -3.1345

Max Act: 2.2022. Min Act: -0.0000

Data Index: 707815 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 3.1345. Min Range: -3.1345

Max Act: 1.9622. Min Act: -0.0000

Data Index: 200380 (C4 (Web Text))

Max Activating Token Index: 536

Text #3

Max Range: 3.1345. Min Range: -3.1345

Max Act: 1.7218. Min Act: 0.0000

Data Index: 1070877 (C4 (Web Text))

Max Activating Token Index: 328

Text #4

Max Range: 3.1345. Min Range: -3.1345

Max Act: 1.7652. Min Act: -0.0000

Data Index: 943033 (C4 (Web Text))

Max Activating Token Index: 207

Text #5

Max Range: 3.1345. Min Range: -3.1345

Max Act: 1.8276. Min Act: -0.0000

Data Index: 1217692 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 3.1345. Min Range: -3.1345

Max Act: 1.7008. Min Act: -0.0000

Data Index: 1166619 (C4 (Web Text))

Max Activating Token Index: 130

Text #7

Max Range: 3.1345. Min Range: -3.1345

Max Act: 1.7853. Min Act: -0.0000

Data Index: 810427 (C4 (Web Text))

Max Activating Token Index: 499

Text #8

Max Range: 3.1345. Min Range: -3.1345

Max Act: 1.6755. Min Act: -0.0000

Data Index: 511833 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 3.1345. Min Range: -3.1345

Max Act: 1.6013. Min Act: -0.0000

Data Index: 114208 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 3.1345. Min Range: -3.1345

Max Act: 1.5216. Min Act: 0.0000

Data Index: 1219365 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 3.1345. Min Range: -3.1345

Max Act: 1.5918. Min Act: -0.0000

Data Index: 1123978 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 3.1345. Min Range: -3.1345

Max Act: 1.5070. Min Act: -0.0000

Data Index: 822561 (C4 (Web Text))

Max Activating Token Index: 136

Text #13

Max Range: 3.1345. Min Range: -3.1345

Max Act: 1.5682. Min Act: -0.0000

Data Index: 1273986 (C4 (Web Text))

Max Activating Token Index: 947

Text #14

Max Range: 3.1345. Min Range: -3.1345

Max Act: 1.4962. Min Act: 0.0000

Data Index: 1164749 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 3.1345. Min Range: -3.1345

Max Act: 1.5418. Min Act: -0.0000

Data Index: 1282598 (C4 (Web Text))

Max Activating Token Index: 447

Text #16

Max Range: 3.1345. Min Range: -3.1345

Max Act: 1.5185. Min Act: -0.0000

Data Index: 1009596 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 3.1345. Min Range: -3.1345

Max Act: 1.4312. Min Act: -0.0000

Data Index: 99728 (C4 (Web Text))

Max Activating Token Index: 588

Text #18

Max Range: 3.1345. Min Range: -3.1345

Max Act: 1.5049. Min Act: -0.0000

Data Index: 42953 (C4 (Web Text))

Max Activating Token Index: 88

Text #19

Max Range: 3.1345. Min Range: -3.1345

Max Act: 1.5011. Min Act: -0.0000

Data Index: 868393 (C4 (Web Text))

Max Activating Token Index: 194