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

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

Neuron 2825 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.8245. Min Act: -0.0000

Data Index: 501522 (C4 (Web Text))

Max Activating Token Index: 675

Text #1

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.7417. Min Act: -0.0000

Data Index: 1120521 (C4 (Web Text))

Max Activating Token Index: 853

Text #2

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.7296. Min Act: -0.0000

Data Index: 467225 (C4 (Web Text))

Max Activating Token Index: 699

Text #3

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.7669. Min Act: -0.0000

Data Index: 456277 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.7794. Min Act: -0.0000

Data Index: 889208 (C4 (Web Text))

Max Activating Token Index: 407

Text #5

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.7501. Min Act: -0.0000

Data Index: 644851 (C4 (Web Text))

Max Activating Token Index: 418

Text #6

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.6443. Min Act: -0.0000

Data Index: 903646 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.7052. Min Act: -0.0000

Data Index: 403902 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.7258. Min Act: -0.0000

Data Index: 407137 (C4 (Web Text))

Max Activating Token Index: 306

Text #9

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.6879. Min Act: -0.0000

Data Index: 77237 (C4 (Web Text))

Max Activating Token Index: 653

Text #10

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.6304. Min Act: -0.0000

Data Index: 204216 (C4 (Web Text))

Max Activating Token Index: 725

Text #11

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.6451. Min Act: -0.0000

Data Index: 1255378 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.5978. Min Act: -0.0000

Data Index: 784092 (C4 (Web Text))

Max Activating Token Index: 827

Text #13

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.6454. Min Act: -0.0000

Data Index: 1174169 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.6257. Min Act: -0.0000

Data Index: 912761 (C4 (Web Text))

Max Activating Token Index: 762

Text #15

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.6083. Min Act: -0.0000

Data Index: 984242 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.6147. Min Act: -0.0000

Data Index: 21387 (C4 (Web Text))

Max Activating Token Index: 952

Text #17

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.6273. Min Act: -0.0000

Data Index: 1263069 (C4 (Web Text))

Max Activating Token Index: 309

Text #18

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.5516. Min Act: -0.0000

Data Index: 178182 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.5114. Min Act: -0.0000

Data Index: 863630 (C4 (Web Text))

Max Activating Token Index: 202