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

Dataset: The Pile

Neuron 4739 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.4290. Min Act: -0.0000

Data Index: 1403815 (The Pile)

Max Activating Token Index: 69

Text #1

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.3141. Min Act: -0.0000

Data Index: 780669 (The Pile)

Max Activating Token Index: 346

Text #2

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.3286. Min Act: -0.0000

Data Index: 1559249 (The Pile)

Max Activating Token Index: 1005

Text #3

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.2577. Min Act: -0.0000

Data Index: 1713682 (The Pile)

Max Activating Token Index: 39

Text #4

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.2343. Min Act: -0.0000

Data Index: 101197 (The Pile)

Max Activating Token Index: 299

Text #5

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.2281. Min Act: -0.0000

Data Index: 281123 (The Pile)

Max Activating Token Index: 629

Text #6

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.3088. Min Act: -0.0000

Data Index: 708634 (The Pile)

Max Activating Token Index: 311

Text #7

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.2618. Min Act: -0.0000

Data Index: 1074305 (The Pile)

Max Activating Token Index: 32

Text #8

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.2228. Min Act: -0.0000

Data Index: 919611 (The Pile)

Max Activating Token Index: 516

Text #9

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.2122. Min Act: -0.0000

Data Index: 474422 (The Pile)

Max Activating Token Index: 1007

Text #10

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.1998. Min Act: -0.0000

Data Index: 1309266 (The Pile)

Max Activating Token Index: 686

Text #11

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.2109. Min Act: -0.0000

Data Index: 1021230 (The Pile)

Max Activating Token Index: 68

Text #12

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.2870. Min Act: -0.0000

Data Index: 1130464 (The Pile)

Max Activating Token Index: 160

Text #13

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.2368. Min Act: -0.0000

Data Index: 872463 (The Pile)

Max Activating Token Index: 181

Text #14

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.2300. Min Act: -0.0000

Data Index: 725791 (The Pile)

Max Activating Token Index: 457

Text #15

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.2155. Min Act: -0.0000

Data Index: 970003 (The Pile)

Max Activating Token Index: 311

Text #16

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.2124. Min Act: -0.0000

Data Index: 1369681 (The Pile)

Max Activating Token Index: 255

Text #17

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.1814. Min Act: -0.0000

Data Index: 774102 (The Pile)

Max Activating Token Index: 115

Text #18

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.2414. Min Act: -0.0000

Data Index: 1174145 (The Pile)

Max Activating Token Index: 978

Text #19

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.1901. Min Act: -0.0000

Data Index: 1696976 (The Pile)

Max Activating Token Index: 987