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

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

Neuron 3686 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: 3.6669. Min Range: -3.6669

Max Act: 3.6669. Min Act: -0.0000

Data Index: 1576720 (Python Code)

Max Activating Token Index: 584

Text #1

Max Range: 3.6669. Min Range: -3.6669

Max Act: 3.4763. Min Act: -0.0000

Data Index: 1539703 (Python Code)

Max Activating Token Index: 43

Text #2

Max Range: 3.6669. Min Range: -3.6669

Max Act: 3.0173. Min Act: -0.0000

Data Index: 1628536 (Python Code)

Max Activating Token Index: 206

Text #3

Max Range: 3.6669. Min Range: -3.6669

Max Act: 2.8374. Min Act: -0.0000

Data Index: 1628010 (Python Code)

Max Activating Token Index: 4

Text #4

Max Range: 3.6669. Min Range: -3.6669

Max Act: 2.7738. Min Act: -0.0000

Data Index: 1302835 (C4 (Web Text))

Max Activating Token Index: 260

Text #5

Max Range: 3.6669. Min Range: -3.6669

Max Act: 2.8683. Min Act: -0.0000

Data Index: 491207 (C4 (Web Text))

Max Activating Token Index: 185

Text #6

Max Range: 3.6669. Min Range: -3.6669

Max Act: 2.8118. Min Act: -0.0000

Data Index: 1416134 (Python Code)

Max Activating Token Index: 400

Text #7

Max Range: 3.6669. Min Range: -3.6669

Max Act: 2.5412. Min Act: -0.0000

Data Index: 1566327 (Python Code)

Max Activating Token Index: 878

Text #8

Max Range: 3.6669. Min Range: -3.6669

Max Act: 2.8068. Min Act: -0.0000

Data Index: 1396130 (Python Code)

Max Activating Token Index: 75

Text #9

Max Range: 3.6669. Min Range: -3.6669

Max Act: 2.7704. Min Act: -0.0000

Data Index: 1361834 (Python Code)

Max Activating Token Index: 313

Text #10

Max Range: 3.6669. Min Range: -3.6669

Max Act: 2.7525. Min Act: -0.0000

Data Index: 1396277 (Python Code)

Max Activating Token Index: 45

Text #11

Max Range: 3.6669. Min Range: -3.6669

Max Act: 2.6113. Min Act: -0.0000

Data Index: 1404968 (Python Code)

Max Activating Token Index: 645

Text #12

Max Range: 3.6669. Min Range: -3.6669

Max Act: 2.5685. Min Act: -0.0000

Data Index: 1628351 (Python Code)

Max Activating Token Index: 238

Text #13

Max Range: 3.6669. Min Range: -3.6669

Max Act: 2.5594. Min Act: -0.0000

Data Index: 1646638 (Python Code)

Max Activating Token Index: 412

Text #14

Max Range: 3.6669. Min Range: -3.6669

Max Act: 2.6750. Min Act: -0.0000

Data Index: 1479564 (Python Code)

Max Activating Token Index: 941

Text #15

Max Range: 3.6669. Min Range: -3.6669

Max Act: 2.5892. Min Act: -0.0000

Data Index: 487124 (C4 (Web Text))

Max Activating Token Index: 649

Text #16

Max Range: 3.6669. Min Range: -3.6669

Max Act: 2.5789. Min Act: -0.0000

Data Index: 1636283 (Python Code)

Max Activating Token Index: 192

Text #17

Max Range: 3.6669. Min Range: -3.6669

Max Act: 2.5736. Min Act: -0.0000

Data Index: 1379359 (Python Code)

Max Activating Token Index: 119

Text #18

Max Range: 3.6669. Min Range: -3.6669

Max Act: 2.4441. Min Act: -0.0000

Data Index: 1378215 (Python Code)

Max Activating Token Index: 252

Text #19

Max Range: 3.6669. Min Range: -3.6669

Max Act: 2.5575. Min Act: -0.0000

Data Index: 1437957 (Python Code)

Max Activating Token Index: 262