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

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

Neuron 4431 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: 0.8066. Min Range: -0.8066

Max Act: 0.8066. Min Act: -0.0000

Data Index: 1339851 (C4 (Web Text))

Max Activating Token Index: 813

Text #1

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.7219. Min Act: -0.0000

Data Index: 924097 (C4 (Web Text))

Max Activating Token Index: 926

Text #2

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.6696. Min Act: -0.0000

Data Index: 820059 (C4 (Web Text))

Max Activating Token Index: 468

Text #3

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.6784. Min Act: -0.0000

Data Index: 1008424 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.5982. Min Act: -0.0000

Data Index: 1205003 (C4 (Web Text))

Max Activating Token Index: 926

Text #5

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.5442. Min Act: -0.0000

Data Index: 162794 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.5551. Min Act: -0.0000

Data Index: 340550 (C4 (Web Text))

Max Activating Token Index: 630

Text #7

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.5095. Min Act: -0.0000

Data Index: 179691 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.5021. Min Act: -0.0000

Data Index: 22257 (C4 (Web Text))

Max Activating Token Index: 315

Text #9

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.4717. Min Act: -0.0000

Data Index: 277115 (C4 (Web Text))

Max Activating Token Index: 729

Text #10

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.4877. Min Act: -0.0000

Data Index: 893573 (C4 (Web Text))

Max Activating Token Index: 731

Text #11

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.4602. Min Act: -0.0000

Data Index: 615497 (C4 (Web Text))

Max Activating Token Index: 890

Text #12

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.4833. Min Act: -0.0000

Data Index: 686338 (C4 (Web Text))

Max Activating Token Index: 510

Text #13

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.4554. Min Act: -0.0000

Data Index: 493748 (C4 (Web Text))

Max Activating Token Index: 887

Text #14

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.4851. Min Act: -0.0000

Data Index: 1194043 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.4769. Min Act: -0.0000

Data Index: 496456 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.4336. Min Act: -0.0000

Data Index: 1141433 (C4 (Web Text))

Max Activating Token Index: 297

Text #17

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.4713. Min Act: -0.0000

Data Index: 1053666 (C4 (Web Text))

Max Activating Token Index: 879

Text #18

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.4390. Min Act: -0.0000

Data Index: 881978 (C4 (Web Text))

Max Activating Token Index: 642

Text #19

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.4013. Min Act: -0.0000

Data Index: 224347 (C4 (Web Text))

Max Activating Token Index: 870