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

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

Neuron 1738 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: 1.0236. Min Range: -1.0236

Max Act: 1.0236. Min Act: -0.0000

Data Index: 512536 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.9337. Min Act: -0.0000

Data Index: 129195 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.9498. Min Act: -0.0000

Data Index: 71717 (C4 (Web Text))

Max Activating Token Index: 910

Text #3

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.8235. Min Act: -0.0000

Data Index: 1082081 (C4 (Web Text))

Max Activating Token Index: 209

Text #4

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.8674. Min Act: -0.0000

Data Index: 1009725 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.8618. Min Act: -0.0000

Data Index: 851197 (C4 (Web Text))

Max Activating Token Index: 756

Text #6

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.7885. Min Act: -0.0000

Data Index: 1092919 (C4 (Web Text))

Max Activating Token Index: 477

Text #7

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.8347. Min Act: -0.0000

Data Index: 324816 (C4 (Web Text))

Max Activating Token Index: 401

Text #8

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.7995. Min Act: -0.0000

Data Index: 89345 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.8206. Min Act: -0.0000

Data Index: 309889 (C4 (Web Text))

Max Activating Token Index: 556

Text #10

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.7279. Min Act: -0.0000

Data Index: 1243339 (C4 (Web Text))

Max Activating Token Index: 852

Text #11

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.7655. Min Act: -0.0000

Data Index: 244303 (C4 (Web Text))

Max Activating Token Index: 605

Text #12

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.7545. Min Act: -0.0000

Data Index: 842660 (C4 (Web Text))

Max Activating Token Index: 91

Text #13

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.7767. Min Act: -0.0000

Data Index: 1075268 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.7392. Min Act: -0.0000

Data Index: 1225299 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.7419. Min Act: -0.0000

Data Index: 372345 (C4 (Web Text))

Max Activating Token Index: 865

Text #16

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.7684. Min Act: -0.0000

Data Index: 727190 (C4 (Web Text))

Max Activating Token Index: 479

Text #17

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.7432. Min Act: -0.0000

Data Index: 671553 (C4 (Web Text))

Max Activating Token Index: 678

Text #18

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.6758. Min Act: -0.0000

Data Index: 1161755 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.7156. Min Act: -0.0000

Data Index: 889175 (C4 (Web Text))

Max Activating Token Index: 854