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

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

Neuron 1005 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9349. Min Range: -0.9349

Max Act: 0.9349. Min Act: -0.0000

Data Index: 370341 (C4 (Web Text))

Max Activating Token Index: 400

Text #1

Max Range: 0.9349. Min Range: -0.9349

Max Act: 0.8740. Min Act: -0.0001

Data Index: 653529 (C4 (Web Text))

Max Activating Token Index: 528

Text #2

Max Range: 0.9349. Min Range: -0.9349

Max Act: 0.8228. Min Act: -0.0000

Data Index: 273685 (C4 (Web Text))

Max Activating Token Index: 995

Text #3

Max Range: 0.9349. Min Range: -0.9349

Max Act: 0.8340. Min Act: -0.0000

Data Index: 30875 (C4 (Web Text))

Max Activating Token Index: 523

Text #4

Max Range: 0.9349. Min Range: -0.9349

Max Act: 0.7698. Min Act: -0.0000

Data Index: 886494 (C4 (Web Text))

Max Activating Token Index: 344

Text #5

Max Range: 0.9349. Min Range: -0.9349

Max Act: 0.7678. Min Act: -0.0001

Data Index: 1049514 (C4 (Web Text))

Max Activating Token Index: 490

Text #6

Max Range: 0.9349. Min Range: -0.9349

Max Act: 0.7406. Min Act: -0.0001

Data Index: 1148469 (C4 (Web Text))

Max Activating Token Index: 448

Text #7

Max Range: 0.9349. Min Range: -0.9349

Max Act: 0.6617. Min Act: -0.0000

Data Index: 618243 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 0.9349. Min Range: -0.9349

Max Act: 0.7314. Min Act: -0.0001

Data Index: 150887 (C4 (Web Text))

Max Activating Token Index: 790

Text #9

Max Range: 0.9349. Min Range: -0.9349

Max Act: 0.6744. Min Act: -0.0000

Data Index: 698370 (C4 (Web Text))

Max Activating Token Index: 149

Text #10

Max Range: 0.9349. Min Range: -0.9349

Max Act: 0.6627. Min Act: -0.0000

Data Index: 49848 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 0.9349. Min Range: -0.9349

Max Act: 0.7123. Min Act: -0.0000

Data Index: 356898 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 0.9349. Min Range: -0.9349

Max Act: 0.6593. Min Act: -0.0000

Data Index: 959067 (C4 (Web Text))

Max Activating Token Index: 470

Text #13

Max Range: 0.9349. Min Range: -0.9349

Max Act: 0.6563. Min Act: -0.0001

Data Index: 391221 (C4 (Web Text))

Max Activating Token Index: 963

Text #14

Max Range: 0.9349. Min Range: -0.9349

Max Act: 0.6453. Min Act: -0.0001

Data Index: 791287 (C4 (Web Text))

Max Activating Token Index: 337

Text #15

Max Range: 0.9349. Min Range: -0.9349

Max Act: 0.6485. Min Act: -0.0001

Data Index: 1132404 (C4 (Web Text))

Max Activating Token Index: 1000

Text #16

Max Range: 0.9349. Min Range: -0.9349

Max Act: 0.6058. Min Act: -0.0000

Data Index: 621120 (C4 (Web Text))

Max Activating Token Index: 244

Text #17

Max Range: 0.9349. Min Range: -0.9349

Max Act: 0.5720. Min Act: -0.0000

Data Index: 1267116 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 0.9349. Min Range: -0.9349

Max Act: 0.6006. Min Act: -0.0001

Data Index: 1528179 (Python Code)

Max Activating Token Index: 889

Text #19

Max Range: 0.9349. Min Range: -0.9349

Max Act: 0.5962. Min Act: -0.0000

Data Index: 1498925 (Python Code)

Max Activating Token Index: 813