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

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

Neuron 5504 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.6820. Min Act: -0.0001

Data Index: 1618871 (Python Code)

Max Activating Token Index: 36

Text #1

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.6832. Min Act: -0.0001

Data Index: 1520943 (Python Code)

Max Activating Token Index: 54

Text #2

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.6483. Min Act: -0.0001

Data Index: 1625849 (Python Code)

Max Activating Token Index: 129

Text #3

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.6847. Min Act: -0.0001

Data Index: 1419187 (Python Code)

Max Activating Token Index: 134

Text #4

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.6263. Min Act: -0.0001

Data Index: 1466437 (Python Code)

Max Activating Token Index: 141

Text #5

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.6602. Min Act: -0.0001

Data Index: 1525808 (Python Code)

Max Activating Token Index: 57

Text #6

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.6373. Min Act: -0.0001

Data Index: 1472712 (Python Code)

Max Activating Token Index: 73

Text #7

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.6792. Min Act: -0.0001

Data Index: 1532985 (Python Code)

Max Activating Token Index: 76

Text #8

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.6362. Min Act: -0.0001

Data Index: 1553463 (Python Code)

Max Activating Token Index: 308

Text #9

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.6072. Min Act: -0.0001

Data Index: 1425734 (Python Code)

Max Activating Token Index: 364

Text #10

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.6182. Min Act: -0.0001

Data Index: 1376286 (Python Code)

Max Activating Token Index: 311

Text #11

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.6183. Min Act: -0.0001

Data Index: 1596215 (Python Code)

Max Activating Token Index: 629

Text #12

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.5332. Min Act: -0.0001

Data Index: 1253420 (C4 (Web Text))

Max Activating Token Index: 261

Text #13

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.5824. Min Act: -0.0001

Data Index: 1376878 (Python Code)

Max Activating Token Index: 476

Text #14

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.5954. Min Act: -0.0001

Data Index: 1522654 (Python Code)

Max Activating Token Index: 968

Text #15

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.6130. Min Act: -0.0001

Data Index: 1392705 (Python Code)

Max Activating Token Index: 1014

Text #16

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.6000. Min Act: -0.0001

Data Index: 1350499 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.5854. Min Act: -0.0001

Data Index: 1491877 (Python Code)

Max Activating Token Index: 470

Text #18

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.5771. Min Act: -0.0001

Data Index: 1559178 (Python Code)

Max Activating Token Index: 53

Text #19

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.5886. Min Act: -0.0001

Data Index: 1457848 (Python Code)

Max Activating Token Index: 62