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

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

Neuron 5236 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: 0.8598. Min Range: -0.8598

Max Act: 0.8598. Min Act: -0.0000

Data Index: 1367136 (Python Code)

Max Activating Token Index: 153

Text #1

Max Range: 0.8598. Min Range: -0.8598

Max Act: 0.7609. Min Act: -0.0000

Data Index: 1539782 (Python Code)

Max Activating Token Index: 862

Text #2

Max Range: 0.8598. Min Range: -0.8598

Max Act: 0.7271. Min Act: -0.0000

Data Index: 1410418 (Python Code)

Max Activating Token Index: 40

Text #3

Max Range: 0.8598. Min Range: -0.8598

Max Act: 0.6704. Min Act: -0.0000

Data Index: 1390563 (Python Code)

Max Activating Token Index: 572

Text #4

Max Range: 0.8598. Min Range: -0.8598

Max Act: 0.7019. Min Act: -0.0000

Data Index: 1538127 (Python Code)

Max Activating Token Index: 367

Text #5

Max Range: 0.8598. Min Range: -0.8598

Max Act: 0.6819. Min Act: -0.0000

Data Index: 1409529 (Python Code)

Max Activating Token Index: 20

Text #6

Max Range: 0.8598. Min Range: -0.8598

Max Act: 0.7247. Min Act: -0.0000

Data Index: 1445501 (Python Code)

Max Activating Token Index: 880

Text #7

Max Range: 0.8598. Min Range: -0.8598

Max Act: 0.6683. Min Act: -0.0000

Data Index: 1653049 (Python Code)

Max Activating Token Index: 943

Text #8

Max Range: 0.8598. Min Range: -0.8598

Max Act: 0.6878. Min Act: -0.0000

Data Index: 1605672 (Python Code)

Max Activating Token Index: 398

Text #9

Max Range: 0.8598. Min Range: -0.8598

Max Act: 0.7124. Min Act: -0.0000

Data Index: 1425834 (Python Code)

Max Activating Token Index: 601

Text #10

Max Range: 0.8598. Min Range: -0.8598

Max Act: 0.6605. Min Act: -0.0000

Data Index: 1568979 (Python Code)

Max Activating Token Index: 66

Text #11

Max Range: 0.8598. Min Range: -0.8598

Max Act: 0.6850. Min Act: -0.0000

Data Index: 1566958 (Python Code)

Max Activating Token Index: 428

Text #12

Max Range: 0.8598. Min Range: -0.8598

Max Act: 0.6857. Min Act: -0.0000

Data Index: 1601208 (Python Code)

Max Activating Token Index: 510

Text #13

Max Range: 0.8598. Min Range: -0.8598

Max Act: 0.6101. Min Act: -0.0000

Data Index: 1503042 (Python Code)

Max Activating Token Index: 323

Text #14

Max Range: 0.8598. Min Range: -0.8598

Max Act: 0.6110. Min Act: -0.0000

Data Index: 1554852 (Python Code)

Max Activating Token Index: 1019

Text #15

Max Range: 0.8598. Min Range: -0.8598

Max Act: 0.6503. Min Act: -0.0000

Data Index: 1601812 (Python Code)

Max Activating Token Index: 712

Text #16

Max Range: 0.8598. Min Range: -0.8598

Max Act: 0.6507. Min Act: -0.0000

Data Index: 1557402 (Python Code)

Max Activating Token Index: 976

Text #17

Max Range: 0.8598. Min Range: -0.8598

Max Act: 0.6481. Min Act: -0.0000

Data Index: 1650862 (Python Code)

Max Activating Token Index: 189

Text #18

Max Range: 0.8598. Min Range: -0.8598

Max Act: 0.6700. Min Act: -0.0000

Data Index: 1557218 (Python Code)

Max Activating Token Index: 835

Text #19

Max Range: 0.8598. Min Range: -0.8598

Max Act: 0.6382. Min Act: -0.0000

Data Index: 1475816 (Python Code)

Max Activating Token Index: 112