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

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

Neuron 855 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.4768. Min Act: -0.0000

Data Index: 1214135 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.4532. Min Act: -0.0000

Data Index: 1321592 (C4 (Web Text))

Max Activating Token Index: 814

Text #2

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.4702. Min Act: -0.0000

Data Index: 402366 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.4545. Min Act: -0.0000

Data Index: 31794 (C4 (Web Text))

Max Activating Token Index: 518

Text #4

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.4363. Min Act: -0.0000

Data Index: 584941 (C4 (Web Text))

Max Activating Token Index: 513

Text #5

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.4329. Min Act: -0.0000

Data Index: 1080969 (C4 (Web Text))

Max Activating Token Index: 553

Text #6

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.4296. Min Act: -0.0000

Data Index: 1103229 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.4323. Min Act: -0.0000

Data Index: 6390 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3877. Min Act: -0.0000

Data Index: 38731 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.4019. Min Act: -0.0000

Data Index: 318317 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3951. Min Act: -0.0000

Data Index: 1031323 (C4 (Web Text))

Max Activating Token Index: 957

Text #11

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3921. Min Act: -0.0000

Data Index: 601355 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3820. Min Act: -0.0000

Data Index: 1276907 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3938. Min Act: -0.0000

Data Index: 674021 (C4 (Web Text))

Max Activating Token Index: 532

Text #14

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3902. Min Act: -0.0000

Data Index: 722216 (C4 (Web Text))

Max Activating Token Index: 509

Text #15

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3757. Min Act: -0.0000

Data Index: 806705 (C4 (Web Text))

Max Activating Token Index: 940

Text #16

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.4182. Min Act: -0.0000

Data Index: 1072925 (C4 (Web Text))

Max Activating Token Index: 297

Text #17

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3748. Min Act: -0.0000

Data Index: 475664 (C4 (Web Text))

Max Activating Token Index: 519

Text #18

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3880. Min Act: -0.0000

Data Index: 67002 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3774. Min Act: -0.0000

Data Index: 211277 (C4 (Web Text))

Max Activating Token Index: 833