Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 717 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9496. Min Range: -0.9496

Max Act: 0.8762. Min Act: -0.0001

Data Index: 1603966 (Python Code)

Max Activating Token Index: 374

Text #1

Max Range: 0.9496. Min Range: -0.9496

Max Act: 0.9496. Min Act: -0.0001

Data Index: 1066776 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 0.9496. Min Range: -0.9496

Max Act: 0.9004. Min Act: -0.0001

Data Index: 1642525 (Python Code)

Max Activating Token Index: 904

Text #3

Max Range: 0.9496. Min Range: -0.9496

Max Act: 0.8363. Min Act: -0.0001

Data Index: 1326919 (C4 (Web Text))

Max Activating Token Index: 930

Text #4

Max Range: 0.9496. Min Range: -0.9496

Max Act: 0.8025. Min Act: -0.0001

Data Index: 513533 (C4 (Web Text))

Max Activating Token Index: 815

Text #5

Max Range: 0.9496. Min Range: -0.9496

Max Act: 0.8304. Min Act: -0.0001

Data Index: 1528509 (Python Code)

Max Activating Token Index: 695

Text #6

Max Range: 0.9496. Min Range: -0.9496

Max Act: 0.8377. Min Act: -0.0001

Data Index: 1383063 (Python Code)

Max Activating Token Index: 131

Text #7

Max Range: 0.9496. Min Range: -0.9496

Max Act: 0.8109. Min Act: -0.0001

Data Index: 487743 (C4 (Web Text))

Max Activating Token Index: 375

Text #8

Max Range: 0.9496. Min Range: -0.9496

Max Act: 0.8761. Min Act: -0.0001

Data Index: 1550501 (Python Code)

Max Activating Token Index: 176

Text #9

Max Range: 0.9496. Min Range: -0.9496

Max Act: 0.8030. Min Act: -0.0001

Data Index: 1300777 (C4 (Web Text))

Max Activating Token Index: 116

Text #10

Max Range: 0.9496. Min Range: -0.9496

Max Act: 0.7714. Min Act: -0.0001

Data Index: 372977 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 0.9496. Min Range: -0.9496

Max Act: 0.7941. Min Act: -0.0001

Data Index: 850045 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 0.9496. Min Range: -0.9496

Max Act: 0.7965. Min Act: -0.0001

Data Index: 803396 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 0.9496. Min Range: -0.9496

Max Act: 0.7715. Min Act: -0.0001

Data Index: 990181 (C4 (Web Text))

Max Activating Token Index: 466

Text #14

Max Range: 0.9496. Min Range: -0.9496

Max Act: 0.7673. Min Act: -0.0001

Data Index: 191886 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 0.9496. Min Range: -0.9496

Max Act: 0.7193. Min Act: -0.0001

Data Index: 1374667 (Python Code)

Max Activating Token Index: 665

Text #16

Max Range: 0.9496. Min Range: -0.9496

Max Act: 0.7502. Min Act: -0.0001

Data Index: 1599501 (Python Code)

Max Activating Token Index: 1021

Text #17

Max Range: 0.9496. Min Range: -0.9496

Max Act: 0.7564. Min Act: -0.0001

Data Index: 1460377 (Python Code)

Max Activating Token Index: 177

Text #18

Max Range: 0.9496. Min Range: -0.9496

Max Act: 0.7580. Min Act: -0.0001

Data Index: 1557638 (Python Code)

Max Activating Token Index: 928

Text #19

Max Range: 0.9496. Min Range: -0.9496

Max Act: 0.7455. Min Act: -0.0001

Data Index: 193163 (C4 (Web Text))

Max Activating Token Index: 408