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

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

Neuron 1790 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.9507. Min Act: -0.0001

Data Index: 822822 (C4 (Web Text))

Max Activating Token Index: 981

Text #1

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.9712. Min Act: -0.0001

Data Index: 1254057 (C4 (Web Text))

Max Activating Token Index: 963

Text #2

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.8919. Min Act: -0.0001

Data Index: 1248891 (C4 (Web Text))

Max Activating Token Index: 749

Text #3

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.8210. Min Act: -0.0001

Data Index: 1056873 (C4 (Web Text))

Max Activating Token Index: 819

Text #4

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.8832. Min Act: -0.0001

Data Index: 898229 (C4 (Web Text))

Max Activating Token Index: 691

Text #5

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.7469. Min Act: -0.0001

Data Index: 169119 (C4 (Web Text))

Max Activating Token Index: 924

Text #6

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.8044. Min Act: -0.0001

Data Index: 848645 (C4 (Web Text))

Max Activating Token Index: 988

Text #7

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.8187. Min Act: -0.0001

Data Index: 417580 (C4 (Web Text))

Max Activating Token Index: 811

Text #8

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.7606. Min Act: -0.0001

Data Index: 837340 (C4 (Web Text))

Max Activating Token Index: 927

Text #9

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.7107. Min Act: -0.0001

Data Index: 192272 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.7413. Min Act: -0.0001

Data Index: 1075404 (C4 (Web Text))

Max Activating Token Index: 557

Text #11

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.7420. Min Act: -0.0001

Data Index: 524766 (C4 (Web Text))

Max Activating Token Index: 470

Text #12

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.7709. Min Act: -0.0001

Data Index: 835691 (C4 (Web Text))

Max Activating Token Index: 795

Text #13

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.7258. Min Act: -0.0001

Data Index: 1352 (C4 (Web Text))

Max Activating Token Index: 298

Text #14

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.6577. Min Act: -0.0001

Data Index: 61730 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.6179. Min Act: -0.0001

Data Index: 1330716 (C4 (Web Text))

Max Activating Token Index: 715

Text #16

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.7301. Min Act: -0.0001

Data Index: 972455 (C4 (Web Text))

Max Activating Token Index: 796

Text #17

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.6418. Min Act: -0.0001

Data Index: 642481 (C4 (Web Text))

Max Activating Token Index: 986

Text #18

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.6638. Min Act: -0.0001

Data Index: 615693 (C4 (Web Text))

Max Activating Token Index: 986

Text #19

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.6391. Min Act: -0.0001

Data Index: 571746 (C4 (Web Text))

Max Activating Token Index: 677