Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2871 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.4054. Min Range: -2.4054

Max Act: 2.4054. Min Act: -0.0000

Data Index: 1640768 (Python Code)

Max Activating Token Index: 868

Text #1

Max Range: 2.4054. Min Range: -2.4054

Max Act: 2.3408. Min Act: -0.0000

Data Index: 968290 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 2.4054. Min Range: -2.4054

Max Act: 1.9553. Min Act: -0.0000

Data Index: 1650844 (Python Code)

Max Activating Token Index: 55

Text #3

Max Range: 2.4054. Min Range: -2.4054

Max Act: 1.7237. Min Act: -0.0000

Data Index: 1473499 (Python Code)

Max Activating Token Index: 525

Text #4

Max Range: 2.4054. Min Range: -2.4054

Max Act: 1.7170. Min Act: -0.0000

Data Index: 1366093 (Python Code)

Max Activating Token Index: 153

Text #5

Max Range: 2.4054. Min Range: -2.4054

Max Act: 1.5864. Min Act: -0.0000

Data Index: 1630409 (Python Code)

Max Activating Token Index: 326

Text #6

Max Range: 2.4054. Min Range: -2.4054

Max Act: 1.6418. Min Act: -0.0000

Data Index: 1645076 (Python Code)

Max Activating Token Index: 755

Text #7

Max Range: 2.4054. Min Range: -2.4054

Max Act: 1.5912. Min Act: -0.0000

Data Index: 1507423 (Python Code)

Max Activating Token Index: 979

Text #8

Max Range: 2.4054. Min Range: -2.4054

Max Act: 1.5860. Min Act: -0.0000

Data Index: 1651145 (Python Code)

Max Activating Token Index: 836

Text #9

Max Range: 2.4054. Min Range: -2.4054

Max Act: 1.4779. Min Act: -0.0000

Data Index: 1449365 (Python Code)

Max Activating Token Index: 38

Text #10

Max Range: 2.4054. Min Range: -2.4054

Max Act: 1.5572. Min Act: 0.0001

Data Index: 252316 (C4 (Web Text))

Max Activating Token Index: 370

Text #11

Max Range: 2.4054. Min Range: -2.4054

Max Act: 1.5233. Min Act: -0.0000

Data Index: 306271 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 2.4054. Min Range: -2.4054

Max Act: 1.5014. Min Act: -0.0000

Data Index: 1504985 (Python Code)

Max Activating Token Index: 736

Text #13

Max Range: 2.4054. Min Range: -2.4054

Max Act: 1.4958. Min Act: -0.0000

Data Index: 1505005 (Python Code)

Max Activating Token Index: 177

Text #14

Max Range: 2.4054. Min Range: -2.4054

Max Act: 1.4849. Min Act: -0.0000

Data Index: 1495051 (Python Code)

Max Activating Token Index: 154

Text #15

Max Range: 2.4054. Min Range: -2.4054

Max Act: 1.4900. Min Act: -0.0000

Data Index: 1398445 (Python Code)

Max Activating Token Index: 594

Text #16

Max Range: 2.4054. Min Range: -2.4054

Max Act: 1.4043. Min Act: -0.0000

Data Index: 1065621 (C4 (Web Text))

Max Activating Token Index: 612

Text #17

Max Range: 2.4054. Min Range: -2.4054

Max Act: 1.3932. Min Act: -0.0000

Data Index: 1364965 (Python Code)

Max Activating Token Index: 977

Text #18

Max Range: 2.4054. Min Range: -2.4054

Max Act: 1.3027. Min Act: -0.0000

Data Index: 1423048 (Python Code)

Max Activating Token Index: 585

Text #19

Max Range: 2.4054. Min Range: -2.4054

Max Act: 1.3752. Min Act: -0.0000

Data Index: 1507536 (Python Code)

Max Activating Token Index: 590