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

Dataset: The Pile

Neuron 4018 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2131. Min Range: -3.2131

Max Act: 2.9647. Min Act: -0.0000

Data Index: 187731 (The Pile)

Max Activating Token Index: 169

Text #1

Max Range: 3.2131. Min Range: -3.2131

Max Act: 3.2131. Min Act: -0.0000

Data Index: 1504877 (The Pile)

Max Activating Token Index: 137

Text #2

Max Range: 3.2131. Min Range: -3.2131

Max Act: 3.1608. Min Act: -0.0000

Data Index: 1368350 (The Pile)

Max Activating Token Index: 723

Text #3

Max Range: 3.2131. Min Range: -3.2131

Max Act: 2.9840. Min Act: -0.0000

Data Index: 655969 (The Pile)

Max Activating Token Index: 878

Text #4

Max Range: 3.2131. Min Range: -3.2131

Max Act: 2.8669. Min Act: -0.0000

Data Index: 1933088 (The Pile)

Max Activating Token Index: 144

Text #5

Max Range: 3.2131. Min Range: -3.2131

Max Act: 2.9856. Min Act: -0.0000

Data Index: 661582 (The Pile)

Max Activating Token Index: 467

Text #6

Max Range: 3.2131. Min Range: -3.2131

Max Act: 2.9798. Min Act: -0.0000

Data Index: 323138 (The Pile)

Max Activating Token Index: 587

Text #7

Max Range: 3.2131. Min Range: -3.2131

Max Act: 2.8893. Min Act: -0.0000

Data Index: 483430 (The Pile)

Max Activating Token Index: 420

Text #8

Max Range: 3.2131. Min Range: -3.2131

Max Act: 2.5041. Min Act: -0.0000

Data Index: 1186425 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 3.2131. Min Range: -3.2131

Max Act: 2.9400. Min Act: -0.0000

Data Index: 1735899 (The Pile)

Max Activating Token Index: 938

Text #10

Max Range: 3.2131. Min Range: -3.2131

Max Act: 2.9765. Min Act: -0.0000

Data Index: 102038 (The Pile)

Max Activating Token Index: 530

Text #11

Max Range: 3.2131. Min Range: -3.2131

Max Act: 2.7255. Min Act: -0.0000

Data Index: 1881020 (The Pile)

Max Activating Token Index: 973

Text #12

Max Range: 3.2131. Min Range: -3.2131

Max Act: 2.7415. Min Act: -0.0000

Data Index: 893550 (The Pile)

Max Activating Token Index: 586

Text #13

Max Range: 3.2131. Min Range: -3.2131

Max Act: 2.9549. Min Act: -0.0000

Data Index: 1059954 (The Pile)

Max Activating Token Index: 911

Text #14

Max Range: 3.2131. Min Range: -3.2131

Max Act: 2.8013. Min Act: -0.0000

Data Index: 731374 (The Pile)

Max Activating Token Index: 298

Text #15

Max Range: 3.2131. Min Range: -3.2131

Max Act: 2.6831. Min Act: -0.0000

Data Index: 1855097 (The Pile)

Max Activating Token Index: 270

Text #16

Max Range: 3.2131. Min Range: -3.2131

Max Act: 2.5627. Min Act: -0.0000

Data Index: 826127 (The Pile)

Max Activating Token Index: 223

Text #17

Max Range: 3.2131. Min Range: -3.2131

Max Act: 2.5348. Min Act: -0.0000

Data Index: 1394164 (The Pile)

Max Activating Token Index: 158

Text #18

Max Range: 3.2131. Min Range: -3.2131

Max Act: 2.5376. Min Act: -0.0000

Data Index: 1270257 (The Pile)

Max Activating Token Index: 283

Text #19

Max Range: 3.2131. Min Range: -3.2131

Max Act: 2.8840. Min Act: -0.0000

Data Index: 654424 (The Pile)

Max Activating Token Index: 956