Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2116 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.8474. Min Act: -0.0000

Data Index: 1399831 (The Pile)

Max Activating Token Index: 277

Text #1

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.7594. Min Act: -0.0000

Data Index: 1235973 (The Pile)

Max Activating Token Index: 622

Text #2

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.7282. Min Act: -0.0000

Data Index: 1593725 (The Pile)

Max Activating Token Index: 829

Text #3

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.6959. Min Act: -0.0000

Data Index: 1305647 (The Pile)

Max Activating Token Index: 37

Text #4

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.7198. Min Act: -0.0000

Data Index: 1965468 (The Pile)

Max Activating Token Index: 232

Text #5

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.7138. Min Act: -0.0000

Data Index: 944873 (The Pile)

Max Activating Token Index: 93

Text #6

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.7149. Min Act: -0.0000

Data Index: 1087828 (The Pile)

Max Activating Token Index: 327

Text #7

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.6672. Min Act: -0.0000

Data Index: 1276988 (The Pile)

Max Activating Token Index: 801

Text #8

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.6859. Min Act: -0.0000

Data Index: 1727813 (The Pile)

Max Activating Token Index: 107

Text #9

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.6760. Min Act: -0.0000

Data Index: 654240 (The Pile)

Max Activating Token Index: 175

Text #10

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.6538. Min Act: -0.0000

Data Index: 1972369 (The Pile)

Max Activating Token Index: 90

Text #11

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.6755. Min Act: -0.0000

Data Index: 1124280 (The Pile)

Max Activating Token Index: 371

Text #12

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.6455. Min Act: -0.0000

Data Index: 1287927 (The Pile)

Max Activating Token Index: 709

Text #13

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.6647. Min Act: -0.0000

Data Index: 127283 (The Pile)

Max Activating Token Index: 812

Text #14

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.6458. Min Act: -0.0000

Data Index: 1465688 (The Pile)

Max Activating Token Index: 328

Text #15

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.6894. Min Act: -0.0000

Data Index: 471228 (The Pile)

Max Activating Token Index: 768

Text #16

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.6442. Min Act: -0.0000

Data Index: 1312806 (The Pile)

Max Activating Token Index: 129

Text #17

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.6857. Min Act: -0.0000

Data Index: 494574 (The Pile)

Max Activating Token Index: 987

Text #18

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.6359. Min Act: -0.0000

Data Index: 993674 (The Pile)

Max Activating Token Index: 55

Text #19

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.6140. Min Act: -0.0000

Data Index: 1261997 (The Pile)

Max Activating Token Index: 315