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

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

Neuron 2695 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: 0.6031. Min Range: -0.6031

Max Act: 0.6031. Min Act: -0.0000

Data Index: 75012 (C4 (Web Text))

Max Activating Token Index: 692

Text #1

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.5799. Min Act: -0.0000

Data Index: 271861 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.5717. Min Act: -0.0000

Data Index: 679993 (C4 (Web Text))

Max Activating Token Index: 138

Text #3

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.5031. Min Act: -0.0000

Data Index: 509923 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.4869. Min Act: -0.0000

Data Index: 357705 (C4 (Web Text))

Max Activating Token Index: 816

Text #5

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.4741. Min Act: -0.0000

Data Index: 676179 (C4 (Web Text))

Max Activating Token Index: 727

Text #6

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.4492. Min Act: -0.0000

Data Index: 568992 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.4684. Min Act: -0.0000

Data Index: 987258 (C4 (Web Text))

Max Activating Token Index: 449

Text #8

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.4984. Min Act: -0.0000

Data Index: 1235395 (C4 (Web Text))

Max Activating Token Index: 372

Text #9

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.4486. Min Act: -0.0000

Data Index: 1084134 (C4 (Web Text))

Max Activating Token Index: 726

Text #10

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.4466. Min Act: -0.0000

Data Index: 791279 (C4 (Web Text))

Max Activating Token Index: 559

Text #11

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.4590. Min Act: -0.0000

Data Index: 190796 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.4451. Min Act: -0.0000

Data Index: 1290020 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.4464. Min Act: -0.0000

Data Index: 1010152 (C4 (Web Text))

Max Activating Token Index: 960

Text #14

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.4533. Min Act: -0.0000

Data Index: 294677 (C4 (Web Text))

Max Activating Token Index: 770

Text #15

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.4410. Min Act: -0.0000

Data Index: 178041 (C4 (Web Text))

Max Activating Token Index: 451

Text #16

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.4108. Min Act: -0.0000

Data Index: 1068997 (C4 (Web Text))

Max Activating Token Index: 208

Text #17

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.4305. Min Act: -0.0000

Data Index: 931687 (C4 (Web Text))

Max Activating Token Index: 616

Text #18

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.4582. Min Act: -0.0000

Data Index: 1105039 (C4 (Web Text))

Max Activating Token Index: 666

Text #19

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.4227. Min Act: -0.0000

Data Index: 1219908 (C4 (Web Text))

Max Activating Token Index: 970