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

Dataset: The Pile

Neuron 3133 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.7252. Min Act: -0.0000

Data Index: 1757430 (The Pile)

Max Activating Token Index: 23

Text #1

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.6188. Min Act: -0.0000

Data Index: 1617985 (The Pile)

Max Activating Token Index: 265

Text #2

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.5601. Min Act: -0.0000

Data Index: 1692555 (The Pile)

Max Activating Token Index: 114

Text #3

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.5138. Min Act: -0.0000

Data Index: 132062 (The Pile)

Max Activating Token Index: 968

Text #4

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.5552. Min Act: -0.0000

Data Index: 859309 (The Pile)

Max Activating Token Index: 49

Text #5

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.5135. Min Act: -0.0000

Data Index: 388553 (The Pile)

Max Activating Token Index: 55

Text #6

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.5276. Min Act: -0.0000

Data Index: 1886091 (The Pile)

Max Activating Token Index: 737

Text #7

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.5039. Min Act: -0.0000

Data Index: 679597 (The Pile)

Max Activating Token Index: 140

Text #8

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.4995. Min Act: -0.0000

Data Index: 1863638 (The Pile)

Max Activating Token Index: 38

Text #9

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.5254. Min Act: -0.0000

Data Index: 1246820 (The Pile)

Max Activating Token Index: 521

Text #10

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.5087. Min Act: -0.0000

Data Index: 745016 (The Pile)

Max Activating Token Index: 203

Text #11

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.4940. Min Act: -0.0000

Data Index: 1482472 (The Pile)

Max Activating Token Index: 224

Text #12

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.4769. Min Act: -0.0000

Data Index: 1916913 (The Pile)

Max Activating Token Index: 719

Text #13

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.4570. Min Act: -0.0000

Data Index: 762688 (The Pile)

Max Activating Token Index: 172

Text #14

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.5174. Min Act: -0.0000

Data Index: 1486820 (The Pile)

Max Activating Token Index: 386

Text #15

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.4849. Min Act: 0.0000

Data Index: 896033 (The Pile)

Max Activating Token Index: 788

Text #16

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.4576. Min Act: -0.0000

Data Index: 864194 (The Pile)

Max Activating Token Index: 67

Text #17

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.4637. Min Act: -0.0000

Data Index: 1591376 (The Pile)

Max Activating Token Index: 525

Text #18

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.4673. Min Act: -0.0000

Data Index: 1823694 (The Pile)

Max Activating Token Index: 78

Text #19

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.4709. Min Act: -0.0000

Data Index: 386106 (The Pile)

Max Activating Token Index: 409