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

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

Neuron 4964 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3806. Min Range: -2.3806

Max Act: 2.1968. Min Act: -0.0000

Data Index: 1389756 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 2.3806. Min Range: -2.3806

Max Act: 2.3806. Min Act: -0.0000

Data Index: 1363643 (Python Code)

Max Activating Token Index: 107

Text #2

Max Range: 2.3806. Min Range: -2.3806

Max Act: 1.8874. Min Act: -0.0000

Data Index: 81604 (C4 (Web Text))

Max Activating Token Index: 507

Text #3

Max Range: 2.3806. Min Range: -2.3806

Max Act: 1.9648. Min Act: -0.0000

Data Index: 1588465 (Python Code)

Max Activating Token Index: 702

Text #4

Max Range: 2.3806. Min Range: -2.3806

Max Act: 1.7716. Min Act: -0.0000

Data Index: 1451331 (Python Code)

Max Activating Token Index: 44

Text #5

Max Range: 2.3806. Min Range: -2.3806

Max Act: 1.8630. Min Act: -0.0000

Data Index: 1597461 (Python Code)

Max Activating Token Index: 964

Text #6

Max Range: 2.3806. Min Range: -2.3806

Max Act: 1.8199. Min Act: -0.0000

Data Index: 1313426 (C4 (Web Text))

Max Activating Token Index: 1011

Text #7

Max Range: 2.3806. Min Range: -2.3806

Max Act: 1.7220. Min Act: -0.0000

Data Index: 1628149 (Python Code)

Max Activating Token Index: 845

Text #8

Max Range: 2.3806. Min Range: -2.3806

Max Act: 1.7815. Min Act: -0.0000

Data Index: 1638789 (Python Code)

Max Activating Token Index: 229

Text #9

Max Range: 2.3806. Min Range: -2.3806

Max Act: 1.7928. Min Act: -0.0000

Data Index: 1618915 (Python Code)

Max Activating Token Index: 496

Text #10

Max Range: 2.3806. Min Range: -2.3806

Max Act: 1.7433. Min Act: -0.0000

Data Index: 1590527 (Python Code)

Max Activating Token Index: 546

Text #11

Max Range: 2.3806. Min Range: -2.3806

Max Act: 1.7358. Min Act: -0.0000

Data Index: 1407743 (Python Code)

Max Activating Token Index: 56

Text #12

Max Range: 2.3806. Min Range: -2.3806

Max Act: 1.7383. Min Act: -0.0000

Data Index: 1221482 (C4 (Web Text))

Max Activating Token Index: 202

Text #13

Max Range: 2.3806. Min Range: -2.3806

Max Act: 1.7342. Min Act: -0.0000

Data Index: 1373146 (Python Code)

Max Activating Token Index: 264

Text #14

Max Range: 2.3806. Min Range: -2.3806

Max Act: 1.7431. Min Act: -0.0000

Data Index: 1480072 (Python Code)

Max Activating Token Index: 939

Text #15

Max Range: 2.3806. Min Range: -2.3806

Max Act: 1.7363. Min Act: -0.0000

Data Index: 1533865 (Python Code)

Max Activating Token Index: 16

Text #16

Max Range: 2.3806. Min Range: -2.3806

Max Act: 1.7103. Min Act: -0.0000

Data Index: 1594323 (Python Code)

Max Activating Token Index: 732

Text #17

Max Range: 2.3806. Min Range: -2.3806

Max Act: 1.6153. Min Act: -0.0000

Data Index: 1368174 (Python Code)

Max Activating Token Index: 574

Text #18

Max Range: 2.3806. Min Range: -2.3806

Max Act: 1.5083. Min Act: -0.0000

Data Index: 1427404 (Python Code)

Max Activating Token Index: 989

Text #19

Max Range: 2.3806. Min Range: -2.3806

Max Act: 1.7797. Min Act: -0.0000

Data Index: 1439270 (Python Code)

Max Activating Token Index: 587