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

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

Neuron 5083 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.4481. Min Act: -0.0000

Data Index: 1007625 (C4 (Web Text))

Max Activating Token Index: 428

Text #1

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.4466. Min Act: -0.0000

Data Index: 619139 (C4 (Web Text))

Max Activating Token Index: 516

Text #2

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.4382. Min Act: -0.0000

Data Index: 376228 (C4 (Web Text))

Max Activating Token Index: 599

Text #3

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.4379. Min Act: -0.0000

Data Index: 872491 (C4 (Web Text))

Max Activating Token Index: 467

Text #4

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.4488. Min Act: -0.0000

Data Index: 667860 (C4 (Web Text))

Max Activating Token Index: 1010

Text #5

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.4135. Min Act: -0.0000

Data Index: 446623 (C4 (Web Text))

Max Activating Token Index: 1003

Text #6

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.4134. Min Act: -0.0000

Data Index: 353338 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.4194. Min Act: -0.0000

Data Index: 529280 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.4034. Min Act: -0.0000

Data Index: 5437 (C4 (Web Text))

Max Activating Token Index: 941

Text #9

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.3927. Min Act: -0.0000

Data Index: 478362 (C4 (Web Text))

Max Activating Token Index: 488

Text #10

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.4298. Min Act: -0.0000

Data Index: 1317784 (C4 (Web Text))

Max Activating Token Index: 734

Text #11

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.3978. Min Act: -0.0000

Data Index: 376565 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.3985. Min Act: -0.0000

Data Index: 642898 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.3850. Min Act: -0.0000

Data Index: 809697 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.3703. Min Act: -0.0000

Data Index: 10802 (C4 (Web Text))

Max Activating Token Index: 953

Text #15

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.3818. Min Act: -0.0000

Data Index: 715783 (C4 (Web Text))

Max Activating Token Index: 540

Text #16

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.3662. Min Act: -0.0000

Data Index: 1163183 (C4 (Web Text))

Max Activating Token Index: 1005

Text #17

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.3642. Min Act: -0.0000

Data Index: 838480 (C4 (Web Text))

Max Activating Token Index: 326

Text #18

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.3873. Min Act: -0.0000

Data Index: 525165 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.3613. Min Act: -0.0000

Data Index: 717500 (C4 (Web Text))

Max Activating Token Index: 640