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

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

Neuron 736 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6821. Min Range: -1.6821

Max Act: 1.6821. Min Act: -0.0000

Data Index: 572382 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 1.6821. Min Range: -1.6821

Max Act: 1.3916. Min Act: -0.0000

Data Index: 1117709 (C4 (Web Text))

Max Activating Token Index: 775

Text #2

Max Range: 1.6821. Min Range: -1.6821

Max Act: 1.1976. Min Act: -0.0000

Data Index: 890783 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 1.6821. Min Range: -1.6821

Max Act: 1.2518. Min Act: -0.0000

Data Index: 843485 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 1.6821. Min Range: -1.6821

Max Act: 1.1643. Min Act: -0.0000

Data Index: 278367 (C4 (Web Text))

Max Activating Token Index: 689

Text #5

Max Range: 1.6821. Min Range: -1.6821

Max Act: 1.2020. Min Act: -0.0000

Data Index: 1325950 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 1.6821. Min Range: -1.6821

Max Act: 1.1073. Min Act: -0.0000

Data Index: 336941 (C4 (Web Text))

Max Activating Token Index: 761

Text #7

Max Range: 1.6821. Min Range: -1.6821

Max Act: 1.1356. Min Act: -0.0000

Data Index: 294715 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 1.6821. Min Range: -1.6821

Max Act: 1.0882. Min Act: -0.0000

Data Index: 1114805 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 1.6821. Min Range: -1.6821

Max Act: 0.9488. Min Act: -0.0000

Data Index: 162145 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 1.6821. Min Range: -1.6821

Max Act: 0.9100. Min Act: -0.0000

Data Index: 758471 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 1.6821. Min Range: -1.6821

Max Act: 0.9669. Min Act: -0.0000

Data Index: 698299 (C4 (Web Text))

Max Activating Token Index: 1017

Text #12

Max Range: 1.6821. Min Range: -1.6821

Max Act: 0.9716. Min Act: -0.0000

Data Index: 326829 (C4 (Web Text))

Max Activating Token Index: 890

Text #13

Max Range: 1.6821. Min Range: -1.6821

Max Act: 0.9205. Min Act: -0.0000

Data Index: 476938 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 1.6821. Min Range: -1.6821

Max Act: 0.9152. Min Act: -0.0000

Data Index: 847138 (C4 (Web Text))

Max Activating Token Index: 307

Text #15

Max Range: 1.6821. Min Range: -1.6821

Max Act: 0.9067. Min Act: -0.0000

Data Index: 305170 (C4 (Web Text))

Max Activating Token Index: 425

Text #16

Max Range: 1.6821. Min Range: -1.6821

Max Act: 0.8783. Min Act: -0.0000

Data Index: 1053662 (C4 (Web Text))

Max Activating Token Index: 90

Text #17

Max Range: 1.6821. Min Range: -1.6821

Max Act: 0.8734. Min Act: -0.0000

Data Index: 99536 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 1.6821. Min Range: -1.6821

Max Act: 0.8806. Min Act: -0.0000

Data Index: 605895 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 1.6821. Min Range: -1.6821

Max Act: 0.8926. Min Act: -0.0000

Data Index: 804244 (C4 (Web Text))

Max Activating Token Index: 72