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

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

Neuron 972 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7354. Min Range: -0.7354

Max Act: 0.7354. Min Act: -0.0000

Data Index: 1551848 (Python Code)

Max Activating Token Index: 817

Text #1

Max Range: 0.7354. Min Range: -0.7354

Max Act: 0.6949. Min Act: -0.0000

Data Index: 1452256 (Python Code)

Max Activating Token Index: 432

Text #2

Max Range: 0.7354. Min Range: -0.7354

Max Act: 0.6088. Min Act: -0.0000

Data Index: 1637388 (Python Code)

Max Activating Token Index: 819

Text #3

Max Range: 0.7354. Min Range: -0.7354

Max Act: 0.6226. Min Act: -0.0000

Data Index: 1592348 (Python Code)

Max Activating Token Index: 803

Text #4

Max Range: 0.7354. Min Range: -0.7354

Max Act: 0.6140. Min Act: -0.0000

Data Index: 1416297 (Python Code)

Max Activating Token Index: 687

Text #5

Max Range: 0.7354. Min Range: -0.7354

Max Act: 0.5829. Min Act: -0.0000

Data Index: 1628879 (Python Code)

Max Activating Token Index: 672

Text #6

Max Range: 0.7354. Min Range: -0.7354

Max Act: 0.5832. Min Act: -0.0000

Data Index: 1572044 (Python Code)

Max Activating Token Index: 127

Text #7

Max Range: 0.7354. Min Range: -0.7354

Max Act: 0.5228. Min Act: -0.0000

Data Index: 1580520 (Python Code)

Max Activating Token Index: 286

Text #8

Max Range: 0.7354. Min Range: -0.7354

Max Act: 0.5771. Min Act: -0.0000

Data Index: 1610897 (Python Code)

Max Activating Token Index: 299

Text #9

Max Range: 0.7354. Min Range: -0.7354

Max Act: 0.5387. Min Act: -0.0000

Data Index: 1450048 (Python Code)

Max Activating Token Index: 195

Text #10

Max Range: 0.7354. Min Range: -0.7354

Max Act: 0.4089. Min Act: 0.0001

Data Index: 1526902 (Python Code)

Max Activating Token Index: 771

Text #11

Max Range: 0.7354. Min Range: -0.7354

Max Act: 0.4533. Min Act: -0.0000

Data Index: 1372616 (Python Code)

Max Activating Token Index: 784

Text #12

Max Range: 0.7354. Min Range: -0.7354

Max Act: 0.4894. Min Act: -0.0000

Data Index: 1124374 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 0.7354. Min Range: -0.7354

Max Act: 0.4319. Min Act: -0.0000

Data Index: 1372161 (Python Code)

Max Activating Token Index: 829

Text #14

Max Range: 0.7354. Min Range: -0.7354

Max Act: 0.4133. Min Act: -0.0000

Data Index: 1543558 (Python Code)

Max Activating Token Index: 374

Text #15

Max Range: 0.7354. Min Range: -0.7354

Max Act: 0.4219. Min Act: -0.0000

Data Index: 831086 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 0.7354. Min Range: -0.7354

Max Act: 0.4715. Min Act: -0.0000

Data Index: 1499386 (Python Code)

Max Activating Token Index: 185

Text #17

Max Range: 0.7354. Min Range: -0.7354

Max Act: 0.4344. Min Act: -0.0000

Data Index: 1463067 (Python Code)

Max Activating Token Index: 104

Text #18

Max Range: 0.7354. Min Range: -0.7354

Max Act: 0.4423. Min Act: -0.0000

Data Index: 1550011 (Python Code)

Max Activating Token Index: 886

Text #19

Max Range: 0.7354. Min Range: -0.7354

Max Act: 0.4167. Min Act: -0.0000

Data Index: 1488191 (Python Code)

Max Activating Token Index: 984