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

Dataset: The Pile

Neuron 4575 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: 0.6477. Min Range: -0.6477

Max Act: 0.6477. Min Act: -0.0000

Data Index: 1452872 (The Pile)

Max Activating Token Index: 221

Text #1

Max Range: 0.6477. Min Range: -0.6477

Max Act: 0.6188. Min Act: -0.0000

Data Index: 841394 (The Pile)

Max Activating Token Index: 15

Text #2

Max Range: 0.6477. Min Range: -0.6477

Max Act: 0.5127. Min Act: -0.0000

Data Index: 1451348 (The Pile)

Max Activating Token Index: 1013

Text #3

Max Range: 0.6477. Min Range: -0.6477

Max Act: 0.5198. Min Act: -0.0000

Data Index: 1919429 (The Pile)

Max Activating Token Index: 186

Text #4

Max Range: 0.6477. Min Range: -0.6477

Max Act: 0.5868. Min Act: -0.0000

Data Index: 1922217 (The Pile)

Max Activating Token Index: 659

Text #5

Max Range: 0.6477. Min Range: -0.6477

Max Act: 0.5332. Min Act: -0.0000

Data Index: 1960567 (The Pile)

Max Activating Token Index: 504

Text #6

Max Range: 0.6477. Min Range: -0.6477

Max Act: 0.5147. Min Act: -0.0000

Data Index: 1420455 (The Pile)

Max Activating Token Index: 969

Text #7

Max Range: 0.6477. Min Range: -0.6477

Max Act: 0.5814. Min Act: -0.0000

Data Index: 365538 (The Pile)

Max Activating Token Index: 186

Text #8

Max Range: 0.6477. Min Range: -0.6477

Max Act: 0.5279. Min Act: -0.0000

Data Index: 1070208 (The Pile)

Max Activating Token Index: 250

Text #9

Max Range: 0.6477. Min Range: -0.6477

Max Act: 0.5604. Min Act: -0.0000

Data Index: 942039 (The Pile)

Max Activating Token Index: 433

Text #10

Max Range: 0.6477. Min Range: -0.6477

Max Act: 0.5148. Min Act: -0.0000

Data Index: 10360 (The Pile)

Max Activating Token Index: 172

Text #11

Max Range: 0.6477. Min Range: -0.6477

Max Act: 0.5537. Min Act: -0.0000

Data Index: 1902370 (The Pile)

Max Activating Token Index: 998

Text #12

Max Range: 0.6477. Min Range: -0.6477

Max Act: 0.5192. Min Act: -0.0000

Data Index: 572828 (The Pile)

Max Activating Token Index: 25

Text #13

Max Range: 0.6477. Min Range: -0.6477

Max Act: 0.5144. Min Act: -0.0000

Data Index: 1231217 (The Pile)

Max Activating Token Index: 184

Text #14

Max Range: 0.6477. Min Range: -0.6477

Max Act: 0.5026. Min Act: -0.0000

Data Index: 674622 (The Pile)

Max Activating Token Index: 37

Text #15

Max Range: 0.6477. Min Range: -0.6477

Max Act: 0.5131. Min Act: -0.0000

Data Index: 290789 (The Pile)

Max Activating Token Index: 409

Text #16

Max Range: 0.6477. Min Range: -0.6477

Max Act: 0.4820. Min Act: -0.0000

Data Index: 1241104 (The Pile)

Max Activating Token Index: 1010

Text #17

Max Range: 0.6477. Min Range: -0.6477

Max Act: 0.4937. Min Act: -0.0000

Data Index: 1031570 (The Pile)

Max Activating Token Index: 1017

Text #18

Max Range: 0.6477. Min Range: -0.6477

Max Act: 0.4888. Min Act: -0.0000

Data Index: 1564324 (The Pile)

Max Activating Token Index: 986

Text #19

Max Range: 0.6477. Min Range: -0.6477

Max Act: 0.4689. Min Act: -0.0000

Data Index: 25466 (The Pile)

Max Activating Token Index: 987