Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 952 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.7270. Min Range: -4.7270

Max Act: 4.7124. Min Act: -0.0000

Data Index: 948964 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 4.7270. Min Range: -4.7270

Max Act: 4.5310. Min Act: -0.0000

Data Index: 169331 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 4.7270. Min Range: -4.7270

Max Act: 4.2816. Min Act: -0.0000

Data Index: 747162 (C4 (Web Text))

Max Activating Token Index: 616

Text #3

Max Range: 4.7270. Min Range: -4.7270

Max Act: 4.6084. Min Act: -0.0000

Data Index: 1267215 (C4 (Web Text))

Max Activating Token Index: 744

Text #4

Max Range: 4.7270. Min Range: -4.7270

Max Act: 4.5485. Min Act: -0.0000

Data Index: 391804 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 4.7270. Min Range: -4.7270

Max Act: 4.5745. Min Act: -0.0000

Data Index: 39662 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 4.7270. Min Range: -4.7270

Max Act: 4.3923. Min Act: -0.0000

Data Index: 1077569 (C4 (Web Text))

Max Activating Token Index: 814

Text #7

Max Range: 4.7270. Min Range: -4.7270

Max Act: 4.3513. Min Act: -0.0000

Data Index: 379059 (C4 (Web Text))

Max Activating Token Index: 190

Text #8

Max Range: 4.7270. Min Range: -4.7270

Max Act: 4.3470. Min Act: -0.0000

Data Index: 840422 (C4 (Web Text))

Max Activating Token Index: 904

Text #9

Max Range: 4.7270. Min Range: -4.7270

Max Act: 4.3412. Min Act: -0.0000

Data Index: 280970 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 4.7270. Min Range: -4.7270

Max Act: 4.7270. Min Act: -0.0000

Data Index: 195636 (C4 (Web Text))

Max Activating Token Index: 155

Text #11

Max Range: 4.7270. Min Range: -4.7270

Max Act: 4.6777. Min Act: -0.0000

Data Index: 813931 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 4.7270. Min Range: -4.7270

Max Act: 4.2459. Min Act: -0.0000

Data Index: 717416 (C4 (Web Text))

Max Activating Token Index: 587

Text #13

Max Range: 4.7270. Min Range: -4.7270

Max Act: 4.4313. Min Act: -0.0000

Data Index: 813552 (C4 (Web Text))

Max Activating Token Index: 735

Text #14

Max Range: 4.7270. Min Range: -4.7270

Max Act: 3.9035. Min Act: -0.0000

Data Index: 861945 (C4 (Web Text))

Max Activating Token Index: 594

Text #15

Max Range: 4.7270. Min Range: -4.7270

Max Act: 4.4340. Min Act: -0.0000

Data Index: 454215 (C4 (Web Text))

Max Activating Token Index: 703

Text #16

Max Range: 4.7270. Min Range: -4.7270

Max Act: 4.2282. Min Act: -0.0000

Data Index: 1051191 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 4.7270. Min Range: -4.7270

Max Act: 4.4458. Min Act: -0.0000

Data Index: 885417 (C4 (Web Text))

Max Activating Token Index: 704

Text #18

Max Range: 4.7270. Min Range: -4.7270

Max Act: 4.3820. Min Act: -0.0000

Data Index: 576928 (C4 (Web Text))

Max Activating Token Index: 808

Text #19

Max Range: 4.7270. Min Range: -4.7270

Max Act: 4.3771. Min Act: -0.0000

Data Index: 1136232 (C4 (Web Text))

Max Activating Token Index: 804