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

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

Neuron 5398 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: 2.4048. Min Range: -2.4048

Max Act: 2.1958. Min Act: -0.0000

Data Index: 21131 (C4 (Web Text))

Max Activating Token Index: 1007

Text #1

Max Range: 2.4048. Min Range: -2.4048

Max Act: 2.4048. Min Act: -0.0000

Data Index: 1617309 (Python Code)

Max Activating Token Index: 363

Text #2

Max Range: 2.4048. Min Range: -2.4048

Max Act: 1.9507. Min Act: -0.0000

Data Index: 1579491 (Python Code)

Max Activating Token Index: 906

Text #3

Max Range: 2.4048. Min Range: -2.4048

Max Act: 2.1099. Min Act: -0.0000

Data Index: 1391175 (Python Code)

Max Activating Token Index: 1018

Text #4

Max Range: 2.4048. Min Range: -2.4048

Max Act: 2.0117. Min Act: -0.0000

Data Index: 865470 (C4 (Web Text))

Max Activating Token Index: 677

Text #5

Max Range: 2.4048. Min Range: -2.4048

Max Act: 2.0834. Min Act: -0.0000

Data Index: 107372 (C4 (Web Text))

Max Activating Token Index: 430

Text #6

Max Range: 2.4048. Min Range: -2.4048

Max Act: 1.8620. Min Act: -0.0000

Data Index: 1630477 (Python Code)

Max Activating Token Index: 292

Text #7

Max Range: 2.4048. Min Range: -2.4048

Max Act: 2.0568. Min Act: -0.0000

Data Index: 1532032 (Python Code)

Max Activating Token Index: 188

Text #8

Max Range: 2.4048. Min Range: -2.4048

Max Act: 1.8386. Min Act: -0.0000

Data Index: 1442948 (Python Code)

Max Activating Token Index: 782

Text #9

Max Range: 2.4048. Min Range: -2.4048

Max Act: 1.9226. Min Act: -0.0000

Data Index: 1607168 (Python Code)

Max Activating Token Index: 427

Text #10

Max Range: 2.4048. Min Range: -2.4048

Max Act: 1.8001. Min Act: -0.0000

Data Index: 1565091 (Python Code)

Max Activating Token Index: 1005

Text #11

Max Range: 2.4048. Min Range: -2.4048

Max Act: 2.0172. Min Act: -0.0000

Data Index: 1577295 (Python Code)

Max Activating Token Index: 506

Text #12

Max Range: 2.4048. Min Range: -2.4048

Max Act: 1.7549. Min Act: -0.0000

Data Index: 1524110 (Python Code)

Max Activating Token Index: 726

Text #13

Max Range: 2.4048. Min Range: -2.4048

Max Act: 1.8793. Min Act: -0.0000

Data Index: 1499094 (Python Code)

Max Activating Token Index: 410

Text #14

Max Range: 2.4048. Min Range: -2.4048

Max Act: 1.7576. Min Act: -0.0000

Data Index: 1605401 (Python Code)

Max Activating Token Index: 157

Text #15

Max Range: 2.4048. Min Range: -2.4048

Max Act: 1.8604. Min Act: -0.0000

Data Index: 1427743 (Python Code)

Max Activating Token Index: 329

Text #16

Max Range: 2.4048. Min Range: -2.4048

Max Act: 1.6423. Min Act: -0.0000

Data Index: 1479290 (Python Code)

Max Activating Token Index: 339

Text #17

Max Range: 2.4048. Min Range: -2.4048

Max Act: 1.7498. Min Act: -0.0000

Data Index: 1583079 (Python Code)

Max Activating Token Index: 547

Text #18

Max Range: 2.4048. Min Range: -2.4048

Max Act: 1.9069. Min Act: -0.0000

Data Index: 1434786 (Python Code)

Max Activating Token Index: 1015

Text #19

Max Range: 2.4048. Min Range: -2.4048

Max Act: 1.9075. Min Act: -0.0000

Data Index: 562913 (C4 (Web Text))

Max Activating Token Index: 375