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

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

Neuron 49 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8805. Min Range: -0.8805

Max Act: 0.8805. Min Act: -0.0001

Data Index: 800880 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 0.8805. Min Range: -0.8805

Max Act: 0.7713. Min Act: -0.0001

Data Index: 885371 (C4 (Web Text))

Max Activating Token Index: 925

Text #2

Max Range: 0.8805. Min Range: -0.8805

Max Act: 0.7410. Min Act: -0.0000

Data Index: 1527810 (Python Code)

Max Activating Token Index: 403

Text #3

Max Range: 0.8805. Min Range: -0.8805

Max Act: 0.8349. Min Act: -0.0001

Data Index: 250492 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 0.8805. Min Range: -0.8805

Max Act: 0.7532. Min Act: -0.0001

Data Index: 778752 (C4 (Web Text))

Max Activating Token Index: 788

Text #5

Max Range: 0.8805. Min Range: -0.8805

Max Act: 0.7779. Min Act: -0.0001

Data Index: 871425 (C4 (Web Text))

Max Activating Token Index: 600

Text #6

Max Range: 0.8805. Min Range: -0.8805

Max Act: 0.7551. Min Act: -0.0001

Data Index: 68467 (C4 (Web Text))

Max Activating Token Index: 304

Text #7

Max Range: 0.8805. Min Range: -0.8805

Max Act: 0.7001. Min Act: -0.0000

Data Index: 683683 (C4 (Web Text))

Max Activating Token Index: 236

Text #8

Max Range: 0.8805. Min Range: -0.8805

Max Act: 0.7140. Min Act: -0.0001

Data Index: 126920 (C4 (Web Text))

Max Activating Token Index: 472

Text #9

Max Range: 0.8805. Min Range: -0.8805

Max Act: 0.6545. Min Act: -0.0001

Data Index: 1222481 (C4 (Web Text))

Max Activating Token Index: 886

Text #10

Max Range: 0.8805. Min Range: -0.8805

Max Act: 0.6602. Min Act: -0.0001

Data Index: 342486 (C4 (Web Text))

Max Activating Token Index: 510

Text #11

Max Range: 0.8805. Min Range: -0.8805

Max Act: 0.6995. Min Act: -0.0001

Data Index: 584251 (C4 (Web Text))

Max Activating Token Index: 595

Text #12

Max Range: 0.8805. Min Range: -0.8805

Max Act: 0.7539. Min Act: -0.0001

Data Index: 177296 (C4 (Web Text))

Max Activating Token Index: 873

Text #13

Max Range: 0.8805. Min Range: -0.8805

Max Act: 0.6753. Min Act: -0.0001

Data Index: 836324 (C4 (Web Text))

Max Activating Token Index: 631

Text #14

Max Range: 0.8805. Min Range: -0.8805

Max Act: 0.7033. Min Act: -0.0001

Data Index: 1327553 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 0.8805. Min Range: -0.8805

Max Act: 0.6586. Min Act: -0.0001

Data Index: 700884 (C4 (Web Text))

Max Activating Token Index: 625

Text #16

Max Range: 0.8805. Min Range: -0.8805

Max Act: 0.7135. Min Act: -0.0001

Data Index: 1057660 (C4 (Web Text))

Max Activating Token Index: 395

Text #17

Max Range: 0.8805. Min Range: -0.8805

Max Act: 0.6717. Min Act: -0.0001

Data Index: 1150825 (C4 (Web Text))

Max Activating Token Index: 281

Text #18

Max Range: 0.8805. Min Range: -0.8805

Max Act: 0.6648. Min Act: -0.0001

Data Index: 678801 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 0.8805. Min Range: -0.8805

Max Act: 0.6860. Min Act: -0.0001

Data Index: 1291180 (C4 (Web Text))

Max Activating Token Index: 462