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

Dataset: The Pile

Neuron 4039 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7994. Min Range: -0.7994

Max Act: 0.7994. Min Act: -0.0000

Data Index: 775491 (The Pile)

Max Activating Token Index: 37

Text #1

Max Range: 0.7994. Min Range: -0.7994

Max Act: 0.6833. Min Act: -0.0000

Data Index: 814510 (The Pile)

Max Activating Token Index: 483

Text #2

Max Range: 0.7994. Min Range: -0.7994

Max Act: 0.6440. Min Act: -0.0000

Data Index: 1069660 (The Pile)

Max Activating Token Index: 97

Text #3

Max Range: 0.7994. Min Range: -0.7994

Max Act: 0.6477. Min Act: -0.0000

Data Index: 1061429 (The Pile)

Max Activating Token Index: 154

Text #4

Max Range: 0.7994. Min Range: -0.7994

Max Act: 0.6313. Min Act: -0.0000

Data Index: 831903 (The Pile)

Max Activating Token Index: 207

Text #5

Max Range: 0.7994. Min Range: -0.7994

Max Act: 0.5928. Min Act: -0.0000

Data Index: 1260342 (The Pile)

Max Activating Token Index: 154

Text #6

Max Range: 0.7994. Min Range: -0.7994

Max Act: 0.5969. Min Act: -0.0000

Data Index: 1332591 (The Pile)

Max Activating Token Index: 329

Text #7

Max Range: 0.7994. Min Range: -0.7994

Max Act: 0.5961. Min Act: -0.0000

Data Index: 1277595 (The Pile)

Max Activating Token Index: 495

Text #8

Max Range: 0.7994. Min Range: -0.7994

Max Act: 0.5935. Min Act: -0.0000

Data Index: 270949 (The Pile)

Max Activating Token Index: 507

Text #9

Max Range: 0.7994. Min Range: -0.7994

Max Act: 0.5706. Min Act: -0.0000

Data Index: 1232064 (The Pile)

Max Activating Token Index: 121

Text #10

Max Range: 0.7994. Min Range: -0.7994

Max Act: 0.5918. Min Act: -0.0000

Data Index: 894200 (The Pile)

Max Activating Token Index: 86

Text #11

Max Range: 0.7994. Min Range: -0.7994

Max Act: 0.5885. Min Act: -0.0000

Data Index: 1593765 (The Pile)

Max Activating Token Index: 258

Text #12

Max Range: 0.7994. Min Range: -0.7994

Max Act: 0.5856. Min Act: 0.0001

Data Index: 1984816 (The Pile)

Max Activating Token Index: 580

Text #13

Max Range: 0.7994. Min Range: -0.7994

Max Act: 0.5543. Min Act: -0.0000

Data Index: 1353689 (The Pile)

Max Activating Token Index: 35

Text #14

Max Range: 0.7994. Min Range: -0.7994

Max Act: 0.5461. Min Act: -0.0000

Data Index: 1956203 (The Pile)

Max Activating Token Index: 143

Text #15

Max Range: 0.7994. Min Range: -0.7994

Max Act: 0.5300. Min Act: -0.0000

Data Index: 379321 (The Pile)

Max Activating Token Index: 557

Text #16

Max Range: 0.7994. Min Range: -0.7994

Max Act: 0.5569. Min Act: -0.0000

Data Index: 1352957 (The Pile)

Max Activating Token Index: 19

Text #17

Max Range: 0.7994. Min Range: -0.7994

Max Act: 0.5317. Min Act: -0.0000

Data Index: 1490474 (The Pile)

Max Activating Token Index: 727

Text #18

Max Range: 0.7994. Min Range: -0.7994

Max Act: 0.5140. Min Act: 0.0000

Data Index: 1559084 (The Pile)

Max Activating Token Index: 61

Text #19

Max Range: 0.7994. Min Range: -0.7994

Max Act: 0.5186. Min Act: -0.0000

Data Index: 62879 (The Pile)

Max Activating Token Index: 22