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

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

Neuron 2099 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2133. Min Range: -1.2133

Max Act: 1.1869. Min Act: -0.0002

Data Index: 266296 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 1.2133. Min Range: -1.2133

Max Act: 1.2133. Min Act: -0.0001

Data Index: 818479 (C4 (Web Text))

Max Activating Token Index: 456

Text #2

Max Range: 1.2133. Min Range: -1.2133

Max Act: 1.0765. Min Act: -0.0002

Data Index: 504686 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 1.2133. Min Range: -1.2133

Max Act: 1.1646. Min Act: -0.0002

Data Index: 98635 (C4 (Web Text))

Max Activating Token Index: 191

Text #4

Max Range: 1.2133. Min Range: -1.2133

Max Act: 1.1408. Min Act: -0.0002

Data Index: 190973 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 1.2133. Min Range: -1.2133

Max Act: 1.1160. Min Act: -0.0002

Data Index: 82740 (C4 (Web Text))

Max Activating Token Index: 1001

Text #6

Max Range: 1.2133. Min Range: -1.2133

Max Act: 1.1182. Min Act: -0.0002

Data Index: 315647 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 1.2133. Min Range: -1.2133

Max Act: 1.1812. Min Act: -0.0001

Data Index: 467036 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 1.2133. Min Range: -1.2133

Max Act: 1.1764. Min Act: -0.0002

Data Index: 441485 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 1.2133. Min Range: -1.2133

Max Act: 1.0008. Min Act: -0.0002

Data Index: 254978 (C4 (Web Text))

Max Activating Token Index: 294

Text #10

Max Range: 1.2133. Min Range: -1.2133

Max Act: 1.0713. Min Act: -0.0002

Data Index: 1158942 (C4 (Web Text))

Max Activating Token Index: 712

Text #11

Max Range: 1.2133. Min Range: -1.2133

Max Act: 1.0640. Min Act: -0.0002

Data Index: 849701 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 1.2133. Min Range: -1.2133

Max Act: 1.1187. Min Act: -0.0002

Data Index: 659614 (C4 (Web Text))

Max Activating Token Index: 995

Text #13

Max Range: 1.2133. Min Range: -1.2133

Max Act: 1.0358. Min Act: -0.0002

Data Index: 411347 (C4 (Web Text))

Max Activating Token Index: 826

Text #14

Max Range: 1.2133. Min Range: -1.2133

Max Act: 0.9374. Min Act: -0.0002

Data Index: 637349 (C4 (Web Text))

Max Activating Token Index: 303

Text #15

Max Range: 1.2133. Min Range: -1.2133

Max Act: 0.9904. Min Act: -0.0002

Data Index: 1158974 (C4 (Web Text))

Max Activating Token Index: 360

Text #16

Max Range: 1.2133. Min Range: -1.2133

Max Act: 1.0796. Min Act: -0.0002

Data Index: 583763 (C4 (Web Text))

Max Activating Token Index: 198

Text #17

Max Range: 1.2133. Min Range: -1.2133

Max Act: 0.9856. Min Act: -0.0001

Data Index: 158408 (C4 (Web Text))

Max Activating Token Index: 906

Text #18

Max Range: 1.2133. Min Range: -1.2133

Max Act: 1.1101. Min Act: -0.0002

Data Index: 767621 (C4 (Web Text))

Max Activating Token Index: 414

Text #19

Max Range: 1.2133. Min Range: -1.2133

Max Act: 1.0372. Min Act: -0.0002

Data Index: 1111157 (C4 (Web Text))

Max Activating Token Index: 410