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

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

Neuron 379 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: 0.7251. Min Range: -0.7251

Max Act: 0.7251. Min Act: -0.0003

Data Index: 753791 (C4 (Web Text))

Max Activating Token Index: 546

Text #1

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.6683. Min Act: -0.0003

Data Index: 638895 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.6932. Min Act: -0.0003

Data Index: 596143 (C4 (Web Text))

Max Activating Token Index: 417

Text #3

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.6884. Min Act: -0.0003

Data Index: 1304 (C4 (Web Text))

Max Activating Token Index: 997

Text #4

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.6054. Min Act: -0.0003

Data Index: 655143 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.6062. Min Act: -0.0003

Data Index: 552912 (C4 (Web Text))

Max Activating Token Index: 558

Text #6

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.5109. Min Act: -0.0003

Data Index: 446773 (C4 (Web Text))

Max Activating Token Index: 588

Text #7

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.6179. Min Act: -0.0003

Data Index: 748173 (C4 (Web Text))

Max Activating Token Index: 247

Text #8

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.6288. Min Act: -0.0003

Data Index: 740131 (C4 (Web Text))

Max Activating Token Index: 262

Text #9

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.5622. Min Act: -0.0003

Data Index: 1243672 (C4 (Web Text))

Max Activating Token Index: 520

Text #10

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.5403. Min Act: -0.0003

Data Index: 592252 (C4 (Web Text))

Max Activating Token Index: 156

Text #11

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.5355. Min Act: -0.0003

Data Index: 201151 (C4 (Web Text))

Max Activating Token Index: 637

Text #12

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.5665. Min Act: -0.0003

Data Index: 1177780 (C4 (Web Text))

Max Activating Token Index: 953

Text #13

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.5751. Min Act: -0.0003

Data Index: 181615 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.5357. Min Act: -0.0003

Data Index: 1206179 (C4 (Web Text))

Max Activating Token Index: 12

Text #15

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.4672. Min Act: -0.0003

Data Index: 915422 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.5523. Min Act: -0.0003

Data Index: 638277 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.5477. Min Act: -0.0003

Data Index: 701295 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.5102. Min Act: -0.0003

Data Index: 703956 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.5284. Min Act: -0.0003

Data Index: 89015 (C4 (Web Text))

Max Activating Token Index: 496