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

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

Neuron 1144 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: 1.1139. Min Range: -1.1139

Max Act: 1.1011. Min Act: -0.0002

Data Index: 82934 (C4 (Web Text))

Max Activating Token Index: 756

Text #1

Max Range: 1.1139. Min Range: -1.1139

Max Act: 1.0696. Min Act: -0.0002

Data Index: 429633 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 1.1139. Min Range: -1.1139

Max Act: 1.1133. Min Act: -0.0002

Data Index: 478737 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 1.1139. Min Range: -1.1139

Max Act: 1.0880. Min Act: -0.0001

Data Index: 922479 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 1.1139. Min Range: -1.1139

Max Act: 0.9705. Min Act: -0.0002

Data Index: 737705 (C4 (Web Text))

Max Activating Token Index: 1005

Text #5

Max Range: 1.1139. Min Range: -1.1139

Max Act: 0.9620. Min Act: -0.0001

Data Index: 477823 (C4 (Web Text))

Max Activating Token Index: 955

Text #6

Max Range: 1.1139. Min Range: -1.1139

Max Act: 1.1116. Min Act: -0.0001

Data Index: 1295206 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 1.1139. Min Range: -1.1139

Max Act: 0.9838. Min Act: -0.0002

Data Index: 1320580 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 1.1139. Min Range: -1.1139

Max Act: 0.9732. Min Act: -0.0001

Data Index: 396535 (C4 (Web Text))

Max Activating Token Index: 764

Text #9

Max Range: 1.1139. Min Range: -1.1139

Max Act: 0.7513. Min Act: -0.0002

Data Index: 1246946 (C4 (Web Text))

Max Activating Token Index: 809

Text #10

Max Range: 1.1139. Min Range: -1.1139

Max Act: 0.7892. Min Act: -0.0002

Data Index: 420959 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 1.1139. Min Range: -1.1139

Max Act: 0.9780. Min Act: -0.0001

Data Index: 408541 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 1.1139. Min Range: -1.1139

Max Act: 0.8838. Min Act: -0.0002

Data Index: 248098 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 1.1139. Min Range: -1.1139

Max Act: 0.9963. Min Act: -0.0002

Data Index: 961948 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 1.1139. Min Range: -1.1139

Max Act: 0.9653. Min Act: -0.0002

Data Index: 1083568 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 1.1139. Min Range: -1.1139

Max Act: 1.1139. Min Act: -0.0001

Data Index: 1188969 (C4 (Web Text))

Max Activating Token Index: 483

Text #16

Max Range: 1.1139. Min Range: -1.1139

Max Act: 0.9770. Min Act: -0.0002

Data Index: 544039 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 1.1139. Min Range: -1.1139

Max Act: 0.8414. Min Act: -0.0002

Data Index: 1277007 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 1.1139. Min Range: -1.1139

Max Act: 0.9793. Min Act: -0.0002

Data Index: 708928 (C4 (Web Text))

Max Activating Token Index: 466

Text #19

Max Range: 1.1139. Min Range: -1.1139

Max Act: 0.9170. Min Act: -0.0002

Data Index: 376307 (C4 (Web Text))

Max Activating Token Index: 898