Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 240 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1216. Min Act: -0.0000

Data Index: 62290 (C4 (Web Text))

Max Activating Token Index: 227

Text #1

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1064. Min Act: -0.0001

Data Index: 822032 (C4 (Web Text))

Max Activating Token Index: 581

Text #2

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0971. Min Act: -0.0000

Data Index: 705497 (C4 (Web Text))

Max Activating Token Index: 543

Text #3

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0949. Min Act: -0.0001

Data Index: 838180 (C4 (Web Text))

Max Activating Token Index: 470

Text #4

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0877. Min Act: -0.0000

Data Index: 540025 (C4 (Web Text))

Max Activating Token Index: 97

Text #5

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0898. Min Act: -0.0001

Data Index: 1068314 (C4 (Web Text))

Max Activating Token Index: 569

Text #6

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0883. Min Act: -0.0001

Data Index: 331509 (C4 (Web Text))

Max Activating Token Index: 763

Text #7

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0875. Min Act: -0.0001

Data Index: 794049 (C4 (Web Text))

Max Activating Token Index: 798

Text #8

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0882. Min Act: 0.0000

Data Index: 972460 (C4 (Web Text))

Max Activating Token Index: 598

Text #9

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0873. Min Act: -0.0001

Data Index: 491925 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0844. Min Act: -0.0001

Data Index: 1047708 (C4 (Web Text))

Max Activating Token Index: 472

Text #11

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0862. Min Act: -0.0001

Data Index: 581281 (C4 (Web Text))

Max Activating Token Index: 240

Text #12

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0865. Min Act: -0.0000

Data Index: 1048188 (C4 (Web Text))

Max Activating Token Index: 470

Text #13

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0834. Min Act: -0.0001

Data Index: 267986 (C4 (Web Text))

Max Activating Token Index: 48

Text #14

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0849. Min Act: -0.0001

Data Index: 1350495 (C4 (Web Text))

Max Activating Token Index: 944

Text #15

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0860. Min Act: -0.0001

Data Index: 464430 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0849. Min Act: -0.0001

Data Index: 1151112 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0788. Min Act: -0.0001

Data Index: 499592 (C4 (Web Text))

Max Activating Token Index: 958

Text #18

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0801. Min Act: -0.0000

Data Index: 29482 (C4 (Web Text))

Max Activating Token Index: 246

Text #19

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0797. Min Act: -0.0000

Data Index: 615562 (C4 (Web Text))

Max Activating Token Index: 249