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

Dataset: The Pile

Neuron 829 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: 1.1372. Min Range: -1.1372

Max Act: 1.1372. Min Act: -0.0000

Data Index: 272766 (The Pile)

Max Activating Token Index: 997

Text #1

Max Range: 1.1372. Min Range: -1.1372

Max Act: 1.1179. Min Act: -0.0000

Data Index: 1320138 (The Pile)

Max Activating Token Index: 435

Text #2

Max Range: 1.1372. Min Range: -1.1372

Max Act: 1.0865. Min Act: -0.0000

Data Index: 1781681 (The Pile)

Max Activating Token Index: 836

Text #3

Max Range: 1.1372. Min Range: -1.1372

Max Act: 1.0656. Min Act: -0.0000

Data Index: 1198426 (The Pile)

Max Activating Token Index: 940

Text #4

Max Range: 1.1372. Min Range: -1.1372

Max Act: 1.0345. Min Act: -0.0000

Data Index: 284011 (The Pile)

Max Activating Token Index: 208

Text #5

Max Range: 1.1372. Min Range: -1.1372

Max Act: 1.0266. Min Act: -0.0000

Data Index: 636793 (The Pile)

Max Activating Token Index: 310

Text #6

Max Range: 1.1372. Min Range: -1.1372

Max Act: 0.9277. Min Act: -0.0000

Data Index: 1123383 (The Pile)

Max Activating Token Index: 782

Text #7

Max Range: 1.1372. Min Range: -1.1372

Max Act: 0.8800. Min Act: -0.0000

Data Index: 1630461 (The Pile)

Max Activating Token Index: 996

Text #8

Max Range: 1.1372. Min Range: -1.1372

Max Act: 0.8797. Min Act: -0.0000

Data Index: 253384 (The Pile)

Max Activating Token Index: 401

Text #9

Max Range: 1.1372. Min Range: -1.1372

Max Act: 0.9037. Min Act: -0.0000

Data Index: 44853 (The Pile)

Max Activating Token Index: 151

Text #10

Max Range: 1.1372. Min Range: -1.1372

Max Act: 0.8954. Min Act: -0.0000

Data Index: 1324361 (The Pile)

Max Activating Token Index: 78

Text #11

Max Range: 1.1372. Min Range: -1.1372

Max Act: 0.8618. Min Act: -0.0000

Data Index: 970536 (The Pile)

Max Activating Token Index: 284

Text #12

Max Range: 1.1372. Min Range: -1.1372

Max Act: 0.8312. Min Act: -0.0000

Data Index: 1136627 (The Pile)

Max Activating Token Index: 720

Text #13

Max Range: 1.1372. Min Range: -1.1372

Max Act: 0.8796. Min Act: -0.0000

Data Index: 484754 (The Pile)

Max Activating Token Index: 191

Text #14

Max Range: 1.1372. Min Range: -1.1372

Max Act: 0.8829. Min Act: -0.0000

Data Index: 1328297 (The Pile)

Max Activating Token Index: 690

Text #15

Max Range: 1.1372. Min Range: -1.1372

Max Act: 0.7981. Min Act: -0.0000

Data Index: 1106354 (The Pile)

Max Activating Token Index: 1019

Text #16

Max Range: 1.1372. Min Range: -1.1372

Max Act: 0.8412. Min Act: -0.0000

Data Index: 1527480 (The Pile)

Max Activating Token Index: 278

Text #17

Max Range: 1.1372. Min Range: -1.1372

Max Act: 0.9245. Min Act: -0.0000

Data Index: 715029 (The Pile)

Max Activating Token Index: 983

Text #18

Max Range: 1.1372. Min Range: -1.1372

Max Act: 0.8576. Min Act: -0.0000

Data Index: 3788 (The Pile)

Max Activating Token Index: 320

Text #19

Max Range: 1.1372. Min Range: -1.1372

Max Act: 0.8644. Min Act: -0.0000

Data Index: 632422 (The Pile)

Max Activating Token Index: 605