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

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

Neuron 5739 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1708. Min Range: -3.1708

Max Act: 3.1708. Min Act: -0.0000

Data Index: 382284 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 3.1708. Min Range: -3.1708

Max Act: 2.9145. Min Act: -0.0000

Data Index: 1202617 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 3.1708. Min Range: -3.1708

Max Act: 2.6941. Min Act: -0.0000

Data Index: 966779 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 3.1708. Min Range: -3.1708

Max Act: 2.7368. Min Act: -0.0000

Data Index: 665590 (C4 (Web Text))

Max Activating Token Index: 158

Text #4

Max Range: 3.1708. Min Range: -3.1708

Max Act: 2.7090. Min Act: -0.0000

Data Index: 1118203 (C4 (Web Text))

Max Activating Token Index: 135

Text #5

Max Range: 3.1708. Min Range: -3.1708

Max Act: 2.6080. Min Act: -0.0000

Data Index: 859196 (C4 (Web Text))

Max Activating Token Index: 712

Text #6

Max Range: 3.1708. Min Range: -3.1708

Max Act: 2.6152. Min Act: -0.0000

Data Index: 228294 (C4 (Web Text))

Max Activating Token Index: 668

Text #7

Max Range: 3.1708. Min Range: -3.1708

Max Act: 2.4481. Min Act: -0.0000

Data Index: 79805 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 3.1708. Min Range: -3.1708

Max Act: 2.5386. Min Act: -0.0000

Data Index: 1210171 (C4 (Web Text))

Max Activating Token Index: 455

Text #9

Max Range: 3.1708. Min Range: -3.1708

Max Act: 2.6548. Min Act: -0.0000

Data Index: 1293871 (C4 (Web Text))

Max Activating Token Index: 679

Text #10

Max Range: 3.1708. Min Range: -3.1708

Max Act: 2.4822. Min Act: -0.0000

Data Index: 404517 (C4 (Web Text))

Max Activating Token Index: 828

Text #11

Max Range: 3.1708. Min Range: -3.1708

Max Act: 2.5078. Min Act: -0.0000

Data Index: 124195 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 3.1708. Min Range: -3.1708

Max Act: 2.1100. Min Act: -0.0000

Data Index: 861426 (C4 (Web Text))

Max Activating Token Index: 416

Text #13

Max Range: 3.1708. Min Range: -3.1708

Max Act: 2.6345. Min Act: -0.0000

Data Index: 1351499 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 3.1708. Min Range: -3.1708

Max Act: 2.3459. Min Act: -0.0000

Data Index: 211349 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 3.1708. Min Range: -3.1708

Max Act: 2.5941. Min Act: -0.0000

Data Index: 585493 (C4 (Web Text))

Max Activating Token Index: 625

Text #16

Max Range: 3.1708. Min Range: -3.1708

Max Act: 2.4437. Min Act: -0.0000

Data Index: 113266 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 3.1708. Min Range: -3.1708

Max Act: 2.4333. Min Act: -0.0000

Data Index: 1289502 (C4 (Web Text))

Max Activating Token Index: 717

Text #18

Max Range: 3.1708. Min Range: -3.1708

Max Act: 2.3053. Min Act: -0.0000

Data Index: 1340815 (C4 (Web Text))

Max Activating Token Index: 121

Text #19

Max Range: 3.1708. Min Range: -3.1708

Max Act: 2.5631. Min Act: -0.0000

Data Index: 1176061 (C4 (Web Text))

Max Activating Token Index: 355