Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 142 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0933. Min Act: -0.0003

Data Index: 325893 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0893. Min Act: -0.0003

Data Index: 41689 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0836. Min Act: -0.0002

Data Index: 901838 (C4 (Web Text))

Max Activating Token Index: 847

Text #3

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0862. Min Act: -0.0003

Data Index: 87264 (C4 (Web Text))

Max Activating Token Index: 627

Text #4

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0835. Min Act: -0.0003

Data Index: 60087 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0794. Min Act: -0.0003

Data Index: 1012385 (C4 (Web Text))

Max Activating Token Index: 266

Text #6

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0769. Min Act: -0.0003

Data Index: 378365 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0763. Min Act: -0.0003

Data Index: 257621 (C4 (Web Text))

Max Activating Token Index: 618

Text #8

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0772. Min Act: -0.0003

Data Index: 605504 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0772. Min Act: -0.0003

Data Index: 777174 (C4 (Web Text))

Max Activating Token Index: 717

Text #10

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0756. Min Act: -0.0003

Data Index: 955481 (C4 (Web Text))

Max Activating Token Index: 43

Text #11

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0772. Min Act: -0.0003

Data Index: 201385 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0747. Min Act: -0.0003

Data Index: 611916 (C4 (Web Text))

Max Activating Token Index: 632

Text #13

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0765. Min Act: -0.0002

Data Index: 1226899 (C4 (Web Text))

Max Activating Token Index: 642

Text #14

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0762. Min Act: -0.0003

Data Index: 93871 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0756. Min Act: -0.0003

Data Index: 840932 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0733. Min Act: -0.0003

Data Index: 654958 (C4 (Web Text))

Max Activating Token Index: 202

Text #17

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0743. Min Act: -0.0004

Data Index: 251860 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0751. Min Act: -0.0002

Data Index: 283900 (C4 (Web Text))

Max Activating Token Index: 302

Text #19

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0740. Min Act: -0.0002

Data Index: 1070681 (C4 (Web Text))

Max Activating Token Index: 407