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

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

Neuron 3833 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.4714. Min Act: -0.0001

Data Index: 215622 (C4 (Web Text))

Max Activating Token Index: 422

Text #1

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.3274. Min Act: -0.0001

Data Index: 1122108 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.2813. Min Act: -0.0001

Data Index: 795005 (C4 (Web Text))

Max Activating Token Index: 850

Text #3

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.2747. Min Act: -0.0001

Data Index: 339773 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.2456. Min Act: -0.0001

Data Index: 1183252 (C4 (Web Text))

Max Activating Token Index: 235

Text #5

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.2379. Min Act: -0.0001

Data Index: 307798 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.2765. Min Act: -0.0001

Data Index: 594179 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.2502. Min Act: -0.0001

Data Index: 886978 (C4 (Web Text))

Max Activating Token Index: 992

Text #8

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.2820. Min Act: -0.0001

Data Index: 110267 (C4 (Web Text))

Max Activating Token Index: 734

Text #9

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.2522. Min Act: -0.0001

Data Index: 1338561 (C4 (Web Text))

Max Activating Token Index: 967

Text #10

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.2473. Min Act: -0.0001

Data Index: 173115 (C4 (Web Text))

Max Activating Token Index: 1004

Text #11

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.2754. Min Act: -0.0001

Data Index: 795116 (C4 (Web Text))

Max Activating Token Index: 300

Text #12

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.2173. Min Act: -0.0001

Data Index: 530470 (C4 (Web Text))

Max Activating Token Index: 236

Text #13

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.2589. Min Act: -0.0001

Data Index: 1223581 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.2110. Min Act: -0.0001

Data Index: 759298 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.2391. Min Act: -0.0001

Data Index: 628121 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.2254. Min Act: -0.0001

Data Index: 54988 (C4 (Web Text))

Max Activating Token Index: 673

Text #17

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.2140. Min Act: -0.0001

Data Index: 497915 (C4 (Web Text))

Max Activating Token Index: 378

Text #18

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.2288. Min Act: -0.0001

Data Index: 787784 (C4 (Web Text))

Max Activating Token Index: 516

Text #19

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.2342. Min Act: -0.0001

Data Index: 1246953 (C4 (Web Text))

Max Activating Token Index: 932