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

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

Neuron 1402 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.7624. Min Act: -0.0000

Data Index: 1515437 (Python Code)

Max Activating Token Index: 899

Text #1

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.8181. Min Act: -0.0000

Data Index: 1613701 (Python Code)

Max Activating Token Index: 497

Text #2

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.8128. Min Act: -0.0000

Data Index: 1484311 (Python Code)

Max Activating Token Index: 580

Text #3

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.8033. Min Act: -0.0000

Data Index: 1481387 (Python Code)

Max Activating Token Index: 45

Text #4

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.6432. Min Act: -0.0000

Data Index: 1484688 (Python Code)

Max Activating Token Index: 728

Text #5

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.6510. Min Act: -0.0000

Data Index: 1589555 (Python Code)

Max Activating Token Index: 1003

Text #6

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.7085. Min Act: -0.0000

Data Index: 1575924 (Python Code)

Max Activating Token Index: 496

Text #7

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.5811. Min Act: -0.0000

Data Index: 1422820 (Python Code)

Max Activating Token Index: 287

Text #8

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.6711. Min Act: -0.0000

Data Index: 1487784 (Python Code)

Max Activating Token Index: 784

Text #9

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.6656. Min Act: -0.0000

Data Index: 1649669 (Python Code)

Max Activating Token Index: 969

Text #10

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.6234. Min Act: -0.0000

Data Index: 1504647 (Python Code)

Max Activating Token Index: 398

Text #11

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.5960. Min Act: -0.0000

Data Index: 1632991 (Python Code)

Max Activating Token Index: 753

Text #12

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.6892. Min Act: -0.0000

Data Index: 1501622 (Python Code)

Max Activating Token Index: 167

Text #13

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.6864. Min Act: -0.0000

Data Index: 1435554 (Python Code)

Max Activating Token Index: 143

Text #14

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.6412. Min Act: -0.0000

Data Index: 1411418 (Python Code)

Max Activating Token Index: 170

Text #15

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.6184. Min Act: -0.0000

Data Index: 1388919 (Python Code)

Max Activating Token Index: 152

Text #16

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.6295. Min Act: -0.0000

Data Index: 1611492 (Python Code)

Max Activating Token Index: 578

Text #17

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.6305. Min Act: -0.0000

Data Index: 1483662 (Python Code)

Max Activating Token Index: 822

Text #18

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.6356. Min Act: -0.0000

Data Index: 1601337 (Python Code)

Max Activating Token Index: 801

Text #19

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.5930. Min Act: -0.0000

Data Index: 1418054 (Python Code)

Max Activating Token Index: 695