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

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

Neuron 3589 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.7806. Min Act: -0.0001

Data Index: 1264122 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.3994. Min Act: -0.0001

Data Index: 1302443 (C4 (Web Text))

Max Activating Token Index: 252

Text #2

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.4170. Min Act: -0.0001

Data Index: 1580462 (Python Code)

Max Activating Token Index: 488

Text #3

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.3852. Min Act: -0.0001

Data Index: 342829 (C4 (Web Text))

Max Activating Token Index: 477

Text #4

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.3713. Min Act: -0.0001

Data Index: 988262 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.3618. Min Act: -0.0001

Data Index: 609192 (C4 (Web Text))

Max Activating Token Index: 432

Text #6

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.1994. Min Act: -0.0001

Data Index: 336853 (C4 (Web Text))

Max Activating Token Index: 749

Text #7

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.1755. Min Act: -0.0001

Data Index: 599631 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.2087. Min Act: -0.0001

Data Index: 901749 (C4 (Web Text))

Max Activating Token Index: 627

Text #9

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.2331. Min Act: -0.0001

Data Index: 1541437 (Python Code)

Max Activating Token Index: 113

Text #10

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.1781. Min Act: -0.0001

Data Index: 1143889 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.1725. Min Act: -0.0001

Data Index: 97316 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.1683. Min Act: -0.0001

Data Index: 76986 (C4 (Web Text))

Max Activating Token Index: 408

Text #13

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.1907. Min Act: -0.0001

Data Index: 251624 (C4 (Web Text))

Max Activating Token Index: 722

Text #14

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.1347. Min Act: -0.0001

Data Index: 786321 (C4 (Web Text))

Max Activating Token Index: 481

Text #15

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.0719. Min Act: -0.0001

Data Index: 49742 (C4 (Web Text))

Max Activating Token Index: 407

Text #16

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.1413. Min Act: -0.0001

Data Index: 826738 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.0306. Min Act: -0.0001

Data Index: 8720 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.0609. Min Act: -0.0001

Data Index: 1488834 (Python Code)

Max Activating Token Index: 523

Text #19

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.0803. Min Act: -0.0001

Data Index: 1481060 (Python Code)

Max Activating Token Index: 932