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

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

Neuron 3625 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6806. Min Range: -3.6806

Max Act: 3.6806. Min Act: -0.0000

Data Index: 1369192 (Python Code)

Max Activating Token Index: 52

Text #1

Max Range: 3.6806. Min Range: -3.6806

Max Act: 3.2896. Min Act: -0.0000

Data Index: 1433027 (Python Code)

Max Activating Token Index: 232

Text #2

Max Range: 3.6806. Min Range: -3.6806

Max Act: 3.2942. Min Act: -0.0000

Data Index: 1642839 (Python Code)

Max Activating Token Index: 64

Text #3

Max Range: 3.6806. Min Range: -3.6806

Max Act: 3.1137. Min Act: -0.0000

Data Index: 1629525 (Python Code)

Max Activating Token Index: 144

Text #4

Max Range: 3.6806. Min Range: -3.6806

Max Act: 2.8516. Min Act: -0.0000

Data Index: 1395671 (Python Code)

Max Activating Token Index: 833

Text #5

Max Range: 3.6806. Min Range: -3.6806

Max Act: 3.1097. Min Act: -0.0000

Data Index: 1653955 (Python Code)

Max Activating Token Index: 94

Text #6

Max Range: 3.6806. Min Range: -3.6806

Max Act: 3.0738. Min Act: -0.0000

Data Index: 1383843 (Python Code)

Max Activating Token Index: 510

Text #7

Max Range: 3.6806. Min Range: -3.6806

Max Act: 3.2231. Min Act: -0.0000

Data Index: 1656727 (Python Code)

Max Activating Token Index: 847

Text #8

Max Range: 3.6806. Min Range: -3.6806

Max Act: 3.0475. Min Act: -0.0000

Data Index: 1539145 (Python Code)

Max Activating Token Index: 6

Text #9

Max Range: 3.6806. Min Range: -3.6806

Max Act: 2.9993. Min Act: -0.0000

Data Index: 1559937 (Python Code)

Max Activating Token Index: 5

Text #10

Max Range: 3.6806. Min Range: -3.6806

Max Act: 2.9920. Min Act: -0.0000

Data Index: 1614904 (Python Code)

Max Activating Token Index: 352

Text #11

Max Range: 3.6806. Min Range: -3.6806

Max Act: 3.0023. Min Act: -0.0000

Data Index: 1536612 (Python Code)

Max Activating Token Index: 816

Text #12

Max Range: 3.6806. Min Range: -3.6806

Max Act: 2.8330. Min Act: -0.0000

Data Index: 1439887 (Python Code)

Max Activating Token Index: 394

Text #13

Max Range: 3.6806. Min Range: -3.6806

Max Act: 2.8164. Min Act: -0.0000

Data Index: 1527382 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 3.6806. Min Range: -3.6806

Max Act: 2.9358. Min Act: -0.0000

Data Index: 1642475 (Python Code)

Max Activating Token Index: 84

Text #15

Max Range: 3.6806. Min Range: -3.6806

Max Act: 3.0605. Min Act: -0.0000

Data Index: 1383046 (Python Code)

Max Activating Token Index: 7

Text #16

Max Range: 3.6806. Min Range: -3.6806

Max Act: 2.9111. Min Act: -0.0000

Data Index: 1391125 (Python Code)

Max Activating Token Index: 7

Text #17

Max Range: 3.6806. Min Range: -3.6806

Max Act: 2.9031. Min Act: -0.0000

Data Index: 1470616 (Python Code)

Max Activating Token Index: 16

Text #18

Max Range: 3.6806. Min Range: -3.6806

Max Act: 2.8877. Min Act: -0.0000

Data Index: 1510906 (Python Code)

Max Activating Token Index: 115

Text #19

Max Range: 3.6806. Min Range: -3.6806

Max Act: 2.8927. Min Act: -0.0000

Data Index: 1551153 (Python Code)

Max Activating Token Index: 828