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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1180 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.6301. Min Act: -0.0000

Data Index: 762209 (C4 (Web Text))

Max Activating Token Index: 759

Text #1

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.9097. Min Act: -0.0000

Data Index: 1036012 (C4 (Web Text))

Max Activating Token Index: 839

Text #2

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.4346. Min Act: -0.0000

Data Index: 1224209 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.2751. Min Act: -0.0000

Data Index: 1269826 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.2557. Min Act: -0.0000

Data Index: 653993 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.2487. Min Act: -0.0000

Data Index: 120181 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.1155. Min Act: -0.0000

Data Index: 812207 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.1701. Min Act: -0.0000

Data Index: 873361 (C4 (Web Text))

Max Activating Token Index: 187

Text #8

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.1935. Min Act: -0.0000

Data Index: 1270375 (C4 (Web Text))

Max Activating Token Index: 888

Text #9

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.1330. Min Act: -0.0000

Data Index: 1265013 (C4 (Web Text))

Max Activating Token Index: 118

Text #10

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.1077. Min Act: -0.0000

Data Index: 348582 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.1813. Min Act: -0.0000

Data Index: 1115909 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.0646. Min Act: -0.0000

Data Index: 252834 (C4 (Web Text))

Max Activating Token Index: 433

Text #13

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.0423. Min Act: -0.0000

Data Index: 217228 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.0337. Min Act: -0.0000

Data Index: 1302276 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 1.9097. Min Range: -1.9097

Max Act: 0.9814. Min Act: -0.0000

Data Index: 1282484 (C4 (Web Text))

Max Activating Token Index: 728

Text #16

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.1181. Min Act: -0.0001

Data Index: 621786 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.0363. Min Act: -0.0000

Data Index: 251854 (C4 (Web Text))

Max Activating Token Index: 294

Text #18

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.0090. Min Act: -0.0000

Data Index: 710654 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.0037. Min Act: -0.0000

Data Index: 1157631 (C4 (Web Text))

Max Activating Token Index: 884