Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4611 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.8985. Min Act: -0.0000

Data Index: 1596681 (Python Code)

Max Activating Token Index: 852

Text #1

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.8762. Min Act: -0.0000

Data Index: 934009 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.8407. Min Act: -0.0000

Data Index: 1423088 (Python Code)

Max Activating Token Index: 131

Text #3

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.8749. Min Act: -0.0000

Data Index: 1389997 (Python Code)

Max Activating Token Index: 326

Text #4

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.8780. Min Act: -0.0000

Data Index: 1609716 (Python Code)

Max Activating Token Index: 137

Text #5

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.8287. Min Act: -0.0000

Data Index: 1620911 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.9310. Min Act: -0.0000

Data Index: 1654323 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.8374. Min Act: -0.0000

Data Index: 1580527 (Python Code)

Max Activating Token Index: 963

Text #8

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.8054. Min Act: -0.0000

Data Index: 1390524 (Python Code)

Max Activating Token Index: 338

Text #9

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.8541. Min Act: -0.0000

Data Index: 1621062 (Python Code)

Max Activating Token Index: 71

Text #10

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.7795. Min Act: -0.0000

Data Index: 1367408 (Python Code)

Max Activating Token Index: 281

Text #11

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.8547. Min Act: -0.0000

Data Index: 1468393 (Python Code)

Max Activating Token Index: 186

Text #12

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.8216. Min Act: -0.0000

Data Index: 1608653 (Python Code)

Max Activating Token Index: 89

Text #13

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.8140. Min Act: -0.0000

Data Index: 1531400 (Python Code)

Max Activating Token Index: 186

Text #14

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.8664. Min Act: -0.0000

Data Index: 1484264 (Python Code)

Max Activating Token Index: 73

Text #15

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.8310. Min Act: -0.0000

Data Index: 1443403 (Python Code)

Max Activating Token Index: 401

Text #16

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.8326. Min Act: -0.0000

Data Index: 1362081 (Python Code)

Max Activating Token Index: 737

Text #17

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.8263. Min Act: -0.0000

Data Index: 1624254 (Python Code)

Max Activating Token Index: 284

Text #18

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.7743. Min Act: -0.0001

Data Index: 1457062 (Python Code)

Max Activating Token Index: 891

Text #19

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.7970. Min Act: -0.0000

Data Index: 1467315 (Python Code)

Max Activating Token Index: 215