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

Dataset: The Pile

Neuron 560 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: 1.8235. Min Range: -1.8235

Max Act: 1.8235. Min Act: -0.0000

Data Index: 1302570 (The Pile)

Max Activating Token Index: 170

Text #1

Max Range: 1.8235. Min Range: -1.8235

Max Act: 1.7013. Min Act: -0.0000

Data Index: 1634177 (The Pile)

Max Activating Token Index: 431

Text #2

Max Range: 1.8235. Min Range: -1.8235

Max Act: 1.7062. Min Act: -0.0000

Data Index: 1158805 (The Pile)

Max Activating Token Index: 384

Text #3

Max Range: 1.8235. Min Range: -1.8235

Max Act: 1.6821. Min Act: -0.0000

Data Index: 1978924 (The Pile)

Max Activating Token Index: 329

Text #4

Max Range: 1.8235. Min Range: -1.8235

Max Act: 1.6375. Min Act: -0.0000

Data Index: 1002018 (The Pile)

Max Activating Token Index: 841

Text #5

Max Range: 1.8235. Min Range: -1.8235

Max Act: 1.4002. Min Act: -0.0000

Data Index: 1732034 (The Pile)

Max Activating Token Index: 565

Text #6

Max Range: 1.8235. Min Range: -1.8235

Max Act: 1.5379. Min Act: -0.0000

Data Index: 1057812 (The Pile)

Max Activating Token Index: 564

Text #7

Max Range: 1.8235. Min Range: -1.8235

Max Act: 1.6295. Min Act: -0.0000

Data Index: 521813 (The Pile)

Max Activating Token Index: 5

Text #8

Max Range: 1.8235. Min Range: -1.8235

Max Act: 1.4092. Min Act: -0.0000

Data Index: 616558 (The Pile)

Max Activating Token Index: 862

Text #9

Max Range: 1.8235. Min Range: -1.8235

Max Act: 1.4491. Min Act: -0.0000

Data Index: 1543514 (The Pile)

Max Activating Token Index: 328

Text #10

Max Range: 1.8235. Min Range: -1.8235

Max Act: 1.1823. Min Act: -0.0000

Data Index: 984199 (The Pile)

Max Activating Token Index: 196

Text #11

Max Range: 1.8235. Min Range: -1.8235

Max Act: 1.3133. Min Act: -0.0000

Data Index: 1934703 (The Pile)

Max Activating Token Index: 592

Text #12

Max Range: 1.8235. Min Range: -1.8235

Max Act: 1.3762. Min Act: -0.0000

Data Index: 1471328 (The Pile)

Max Activating Token Index: 965

Text #13

Max Range: 1.8235. Min Range: -1.8235

Max Act: 1.2918. Min Act: -0.0000

Data Index: 1753187 (The Pile)

Max Activating Token Index: 578

Text #14

Max Range: 1.8235. Min Range: -1.8235

Max Act: 1.3819. Min Act: -0.0000

Data Index: 1406310 (The Pile)

Max Activating Token Index: 466

Text #15

Max Range: 1.8235. Min Range: -1.8235

Max Act: 1.3861. Min Act: -0.0000

Data Index: 1990840 (The Pile)

Max Activating Token Index: 85

Text #16

Max Range: 1.8235. Min Range: -1.8235

Max Act: 1.3966. Min Act: -0.0000

Data Index: 1557466 (The Pile)

Max Activating Token Index: 116

Text #17

Max Range: 1.8235. Min Range: -1.8235

Max Act: 1.3397. Min Act: -0.0000

Data Index: 601789 (The Pile)

Max Activating Token Index: 854

Text #18

Max Range: 1.8235. Min Range: -1.8235

Max Act: 1.3318. Min Act: -0.0000

Data Index: 1135597 (The Pile)

Max Activating Token Index: 44

Text #19

Max Range: 1.8235. Min Range: -1.8235

Max Act: 1.3016. Min Act: -0.0000

Data Index: 1636170 (The Pile)

Max Activating Token Index: 862