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

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

Neuron 1630 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: 0.8254. Min Range: -0.8254

Max Act: 0.8254. Min Act: -0.0000

Data Index: 422501 (C4 (Web Text))

Max Activating Token Index: 477

Text #1

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.6075. Min Act: -0.0000

Data Index: 690897 (C4 (Web Text))

Max Activating Token Index: 573

Text #2

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.5388. Min Act: -0.0000

Data Index: 821949 (C4 (Web Text))

Max Activating Token Index: 1015

Text #3

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.5487. Min Act: -0.0000

Data Index: 423989 (C4 (Web Text))

Max Activating Token Index: 63

Text #4

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.4680. Min Act: -0.0000

Data Index: 1179189 (C4 (Web Text))

Max Activating Token Index: 696

Text #5

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.5113. Min Act: -0.0000

Data Index: 379152 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.5108. Min Act: -0.0000

Data Index: 942823 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.4967. Min Act: -0.0000

Data Index: 482109 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.4919. Min Act: -0.0000

Data Index: 783387 (C4 (Web Text))

Max Activating Token Index: 738

Text #9

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.4865. Min Act: -0.0000

Data Index: 1296867 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.4740. Min Act: -0.0000

Data Index: 975989 (C4 (Web Text))

Max Activating Token Index: 622

Text #11

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.4971. Min Act: -0.0000

Data Index: 1269211 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.4770. Min Act: -0.0000

Data Index: 258020 (C4 (Web Text))

Max Activating Token Index: 468

Text #13

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.4477. Min Act: -0.0000

Data Index: 1136238 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.4871. Min Act: -0.0000

Data Index: 1080115 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.4740. Min Act: -0.0000

Data Index: 599782 (C4 (Web Text))

Max Activating Token Index: 455

Text #16

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.5077. Min Act: -0.0000

Data Index: 561495 (C4 (Web Text))

Max Activating Token Index: 726

Text #17

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.4703. Min Act: -0.0000

Data Index: 323553 (C4 (Web Text))

Max Activating Token Index: 465

Text #18

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.4785. Min Act: -0.0000

Data Index: 1066411 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.4252. Min Act: -0.0000

Data Index: 930748 (C4 (Web Text))

Max Activating Token Index: 722