Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3980 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.9950. Min Act: -0.0002

Data Index: 1340017 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.9746. Min Act: -0.0002

Data Index: 1097668 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.9378. Min Act: -0.0002

Data Index: 412383 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.9700. Min Act: -0.0002

Data Index: 599664 (C4 (Web Text))

Max Activating Token Index: 643

Text #4

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.9546. Min Act: -0.0002

Data Index: 105837 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.9351. Min Act: -0.0002

Data Index: 1000675 (C4 (Web Text))

Max Activating Token Index: 791

Text #6

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.9329. Min Act: -0.0002

Data Index: 843409 (C4 (Web Text))

Max Activating Token Index: 855

Text #7

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.9254. Min Act: -0.0002

Data Index: 455759 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.9122. Min Act: -0.0002

Data Index: 1164327 (C4 (Web Text))

Max Activating Token Index: 452

Text #9

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.9151. Min Act: -0.0002

Data Index: 1122385 (C4 (Web Text))

Max Activating Token Index: 679

Text #10

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.9092. Min Act: -0.0002

Data Index: 1005938 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.9298. Min Act: -0.0002

Data Index: 838599 (C4 (Web Text))

Max Activating Token Index: 631

Text #12

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.9122. Min Act: -0.0002

Data Index: 1092321 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.9032. Min Act: -0.0002

Data Index: 1134804 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.9155. Min Act: -0.0002

Data Index: 475611 (C4 (Web Text))

Max Activating Token Index: 255

Text #15

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.8963. Min Act: -0.0002

Data Index: 653700 (C4 (Web Text))

Max Activating Token Index: 375

Text #16

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.9113. Min Act: -0.0002

Data Index: 487701 (C4 (Web Text))

Max Activating Token Index: 598

Text #17

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.8808. Min Act: -0.0002

Data Index: 1031232 (C4 (Web Text))

Max Activating Token Index: 97

Text #18

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.9071. Min Act: -0.0002

Data Index: 859476 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.8906. Min Act: -0.0002

Data Index: 828385 (C4 (Web Text))

Max Activating Token Index: 7