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

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

Neuron 3222 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: 1.8829. Min Range: -1.8829

Max Act: 1.8174. Min Act: -0.0000

Data Index: 1488944 (Python Code)

Max Activating Token Index: 23

Text #1

Max Range: 1.8829. Min Range: -1.8829

Max Act: 1.8829. Min Act: -0.0000

Data Index: 1473493 (Python Code)

Max Activating Token Index: 407

Text #2

Max Range: 1.8829. Min Range: -1.8829

Max Act: 1.3127. Min Act: -0.0000

Data Index: 217091 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 1.8829. Min Range: -1.8829

Max Act: 1.4416. Min Act: -0.0000

Data Index: 1403694 (Python Code)

Max Activating Token Index: 136

Text #4

Max Range: 1.8829. Min Range: -1.8829

Max Act: 1.4865. Min Act: -0.0000

Data Index: 1433915 (Python Code)

Max Activating Token Index: 529

Text #5

Max Range: 1.8829. Min Range: -1.8829

Max Act: 1.2788. Min Act: -0.0000

Data Index: 1463389 (Python Code)

Max Activating Token Index: 920

Text #6

Max Range: 1.8829. Min Range: -1.8829

Max Act: 1.3436. Min Act: -0.0000

Data Index: 1587897 (Python Code)

Max Activating Token Index: 383

Text #7

Max Range: 1.8829. Min Range: -1.8829

Max Act: 1.4027. Min Act: -0.0000

Data Index: 1527331 (Python Code)

Max Activating Token Index: 900

Text #8

Max Range: 1.8829. Min Range: -1.8829

Max Act: 1.3092. Min Act: -0.0000

Data Index: 1486370 (Python Code)

Max Activating Token Index: 941

Text #9

Max Range: 1.8829. Min Range: -1.8829

Max Act: 1.1626. Min Act: -0.0000

Data Index: 1594724 (Python Code)

Max Activating Token Index: 529

Text #10

Max Range: 1.8829. Min Range: -1.8829

Max Act: 1.2804. Min Act: -0.0000

Data Index: 1591788 (Python Code)

Max Activating Token Index: 407

Text #11

Max Range: 1.8829. Min Range: -1.8829

Max Act: 1.2587. Min Act: -0.0000

Data Index: 1214658 (C4 (Web Text))

Max Activating Token Index: 264

Text #12

Max Range: 1.8829. Min Range: -1.8829

Max Act: 1.2212. Min Act: -0.0000

Data Index: 1450027 (Python Code)

Max Activating Token Index: 617

Text #13

Max Range: 1.8829. Min Range: -1.8829

Max Act: 1.2150. Min Act: -0.0000

Data Index: 213328 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 1.8829. Min Range: -1.8829

Max Act: 1.2210. Min Act: -0.0000

Data Index: 1631329 (Python Code)

Max Activating Token Index: 896

Text #15

Max Range: 1.8829. Min Range: -1.8829

Max Act: 1.1399. Min Act: -0.0000

Data Index: 1642980 (Python Code)

Max Activating Token Index: 576

Text #16

Max Range: 1.8829. Min Range: -1.8829

Max Act: 1.1306. Min Act: -0.0000

Data Index: 1366823 (Python Code)

Max Activating Token Index: 155

Text #17

Max Range: 1.8829. Min Range: -1.8829

Max Act: 1.1158. Min Act: -0.0000

Data Index: 1560450 (Python Code)

Max Activating Token Index: 16

Text #18

Max Range: 1.8829. Min Range: -1.8829

Max Act: 1.1065. Min Act: -0.0000

Data Index: 1601053 (Python Code)

Max Activating Token Index: 356

Text #19

Max Range: 1.8829. Min Range: -1.8829

Max Act: 1.0930. Min Act: -0.0000

Data Index: 356558 (C4 (Web Text))

Max Activating Token Index: 477