Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1683 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0518. Min Range: -1.0518

Max Act: 1.0518. Min Act: -0.0001

Data Index: 180262 (C4 (Web Text))

Max Activating Token Index: 570

Text #1

Max Range: 1.0518. Min Range: -1.0518

Max Act: 0.9915. Min Act: -0.0000

Data Index: 202919 (C4 (Web Text))

Max Activating Token Index: 666

Text #2

Max Range: 1.0518. Min Range: -1.0518

Max Act: 0.9834. Min Act: -0.0001

Data Index: 1271038 (C4 (Web Text))

Max Activating Token Index: 995

Text #3

Max Range: 1.0518. Min Range: -1.0518

Max Act: 0.9419. Min Act: -0.0001

Data Index: 649958 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 1.0518. Min Range: -1.0518

Max Act: 0.8885. Min Act: -0.0001

Data Index: 550707 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 1.0518. Min Range: -1.0518

Max Act: 0.8777. Min Act: -0.0001

Data Index: 451103 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 1.0518. Min Range: -1.0518

Max Act: 0.8794. Min Act: -0.0001

Data Index: 1166986 (C4 (Web Text))

Max Activating Token Index: 635

Text #7

Max Range: 1.0518. Min Range: -1.0518

Max Act: 0.8483. Min Act: -0.0001

Data Index: 58370 (C4 (Web Text))

Max Activating Token Index: 902

Text #8

Max Range: 1.0518. Min Range: -1.0518

Max Act: 0.8997. Min Act: -0.0000

Data Index: 100228 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 1.0518. Min Range: -1.0518

Max Act: 0.8666. Min Act: -0.0000

Data Index: 370878 (C4 (Web Text))

Max Activating Token Index: 129

Text #10

Max Range: 1.0518. Min Range: -1.0518

Max Act: 0.8503. Min Act: -0.0001

Data Index: 211234 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 1.0518. Min Range: -1.0518

Max Act: 0.8468. Min Act: -0.0000

Data Index: 1288043 (C4 (Web Text))

Max Activating Token Index: 541

Text #12

Max Range: 1.0518. Min Range: -1.0518

Max Act: 0.8153. Min Act: -0.0000

Data Index: 809130 (C4 (Web Text))

Max Activating Token Index: 664

Text #13

Max Range: 1.0518. Min Range: -1.0518

Max Act: 0.7873. Min Act: -0.0000

Data Index: 864720 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 1.0518. Min Range: -1.0518

Max Act: 0.8278. Min Act: -0.0001

Data Index: 1179983 (C4 (Web Text))

Max Activating Token Index: 271

Text #15

Max Range: 1.0518. Min Range: -1.0518

Max Act: 0.8135. Min Act: -0.0000

Data Index: 69092 (C4 (Web Text))

Max Activating Token Index: 563

Text #16

Max Range: 1.0518. Min Range: -1.0518

Max Act: 0.8070. Min Act: -0.0000

Data Index: 850118 (C4 (Web Text))

Max Activating Token Index: 291

Text #17

Max Range: 1.0518. Min Range: -1.0518

Max Act: 0.7834. Min Act: -0.0001

Data Index: 1299409 (C4 (Web Text))

Max Activating Token Index: 346

Text #18

Max Range: 1.0518. Min Range: -1.0518

Max Act: 0.8023. Min Act: -0.0000

Data Index: 988089 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 1.0518. Min Range: -1.0518

Max Act: 0.7505. Min Act: -0.0000

Data Index: 1335201 (C4 (Web Text))

Max Activating Token Index: 633