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

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

Neuron 701 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.9233. Min Act: 0.0000

Data Index: 349113 (C4 (Web Text))

Max Activating Token Index: 321

Text #1

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.9676. Min Act: -0.0000

Data Index: 1611346 (Python Code)

Max Activating Token Index: 39

Text #2

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.8778. Min Act: -0.0000

Data Index: 35271 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.8714. Min Act: -0.0000

Data Index: 1137856 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.7778. Min Act: -0.0000

Data Index: 397953 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.7546. Min Act: -0.0000

Data Index: 1308102 (C4 (Web Text))

Max Activating Token Index: 522

Text #6

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.7348. Min Act: -0.0000

Data Index: 1495979 (Python Code)

Max Activating Token Index: 466

Text #7

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.6855. Min Act: 0.0000

Data Index: 857919 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.7693. Min Act: 0.0000

Data Index: 586355 (C4 (Web Text))

Max Activating Token Index: 809

Text #9

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.6637. Min Act: -0.0000

Data Index: 1647696 (Python Code)

Max Activating Token Index: 49

Text #10

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.7068. Min Act: -0.0000

Data Index: 234895 (C4 (Web Text))

Max Activating Token Index: 713

Text #11

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.6882. Min Act: -0.0000

Data Index: 398910 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.6592. Min Act: -0.0000

Data Index: 1454800 (Python Code)

Max Activating Token Index: 308

Text #13

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.6330. Min Act: -0.0000

Data Index: 1550789 (Python Code)

Max Activating Token Index: 554

Text #14

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.6470. Min Act: -0.0000

Data Index: 1548495 (Python Code)

Max Activating Token Index: 32

Text #15

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.6408. Min Act: -0.0000

Data Index: 611931 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.5566. Min Act: -0.0000

Data Index: 507366 (C4 (Web Text))

Max Activating Token Index: 796

Text #17

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.5983. Min Act: -0.0000

Data Index: 1599016 (Python Code)

Max Activating Token Index: 32

Text #18

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.6165. Min Act: 0.0000

Data Index: 365848 (C4 (Web Text))

Max Activating Token Index: 273

Text #19

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.7111. Min Act: -0.0000

Data Index: 1413125 (Python Code)

Max Activating Token Index: 703