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

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

Neuron 4002 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.9782. Min Act: -0.0000

Data Index: 671396 (C4 (Web Text))

Max Activating Token Index: 849

Text #1

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.9273. Min Act: -0.0000

Data Index: 1066769 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.9106. Min Act: -0.0000

Data Index: 335344 (C4 (Web Text))

Max Activating Token Index: 723

Text #3

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8441. Min Act: -0.0000

Data Index: 509089 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8656. Min Act: -0.0000

Data Index: 459125 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.9254. Min Act: -0.0001

Data Index: 888236 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8636. Min Act: -0.0000

Data Index: 289378 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.7668. Min Act: -0.0000

Data Index: 939317 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8053. Min Act: -0.0000

Data Index: 527955 (C4 (Web Text))

Max Activating Token Index: 723

Text #9

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8734. Min Act: -0.0000

Data Index: 605282 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.9361. Min Act: -0.0000

Data Index: 1054579 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8276. Min Act: -0.0000

Data Index: 543041 (C4 (Web Text))

Max Activating Token Index: 432

Text #12

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8050. Min Act: -0.0000

Data Index: 806957 (C4 (Web Text))

Max Activating Token Index: 257

Text #13

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8582. Min Act: -0.0000

Data Index: 681012 (C4 (Web Text))

Max Activating Token Index: 96

Text #14

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8274. Min Act: -0.0000

Data Index: 1031852 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.7362. Min Act: -0.0000

Data Index: 657674 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8690. Min Act: -0.0000

Data Index: 16984 (C4 (Web Text))

Max Activating Token Index: 790

Text #17

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.7757. Min Act: -0.0000

Data Index: 427060 (C4 (Web Text))

Max Activating Token Index: 48

Text #18

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.7903. Min Act: -0.0000

Data Index: 511575 (C4 (Web Text))

Max Activating Token Index: 379

Text #19

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.7519. Min Act: -0.0000

Data Index: 500538 (C4 (Web Text))

Max Activating Token Index: 744