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

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

Neuron 1632 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6873. Min Range: -1.6873

Max Act: 1.6873. Min Act: -0.0001

Data Index: 1300449 (C4 (Web Text))

Max Activating Token Index: 452

Text #1

Max Range: 1.6873. Min Range: -1.6873

Max Act: 1.5210. Min Act: -0.0001

Data Index: 935721 (C4 (Web Text))

Max Activating Token Index: 876

Text #2

Max Range: 1.6873. Min Range: -1.6873

Max Act: 1.5029. Min Act: -0.0002

Data Index: 283723 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 1.6873. Min Range: -1.6873

Max Act: 1.5824. Min Act: -0.0002

Data Index: 858973 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 1.6873. Min Range: -1.6873

Max Act: 1.5634. Min Act: -0.0002

Data Index: 1118700 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 1.6873. Min Range: -1.6873

Max Act: 1.5193. Min Act: -0.0002

Data Index: 506048 (C4 (Web Text))

Max Activating Token Index: 766

Text #6

Max Range: 1.6873. Min Range: -1.6873

Max Act: 1.4999. Min Act: -0.0001

Data Index: 139643 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 1.6873. Min Range: -1.6873

Max Act: 1.5454. Min Act: -0.0001

Data Index: 1283482 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 1.6873. Min Range: -1.6873

Max Act: 1.5814. Min Act: -0.0002

Data Index: 279510 (C4 (Web Text))

Max Activating Token Index: 617

Text #9

Max Range: 1.6873. Min Range: -1.6873

Max Act: 1.4104. Min Act: -0.0001

Data Index: 712233 (C4 (Web Text))

Max Activating Token Index: 285

Text #10

Max Range: 1.6873. Min Range: -1.6873

Max Act: 1.3792. Min Act: -0.0001

Data Index: 1084480 (C4 (Web Text))

Max Activating Token Index: 848

Text #11

Max Range: 1.6873. Min Range: -1.6873

Max Act: 1.3704. Min Act: -0.0002

Data Index: 327053 (C4 (Web Text))

Max Activating Token Index: 957

Text #12

Max Range: 1.6873. Min Range: -1.6873

Max Act: 1.4133. Min Act: -0.0002

Data Index: 917190 (C4 (Web Text))

Max Activating Token Index: 359

Text #13

Max Range: 1.6873. Min Range: -1.6873

Max Act: 1.3448. Min Act: -0.0002

Data Index: 118746 (C4 (Web Text))

Max Activating Token Index: 777

Text #14

Max Range: 1.6873. Min Range: -1.6873

Max Act: 1.2920. Min Act: -0.0001

Data Index: 774502 (C4 (Web Text))

Max Activating Token Index: 833

Text #15

Max Range: 1.6873. Min Range: -1.6873

Max Act: 1.3997. Min Act: -0.0002

Data Index: 339401 (C4 (Web Text))

Max Activating Token Index: 935

Text #16

Max Range: 1.6873. Min Range: -1.6873

Max Act: 1.4053. Min Act: -0.0002

Data Index: 122896 (C4 (Web Text))

Max Activating Token Index: 516

Text #17

Max Range: 1.6873. Min Range: -1.6873

Max Act: 1.3933. Min Act: -0.0002

Data Index: 1273123 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 1.6873. Min Range: -1.6873

Max Act: 1.4195. Min Act: -0.0002

Data Index: 21597 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 1.6873. Min Range: -1.6873

Max Act: 1.4651. Min Act: -0.0001

Data Index: 344325 (C4 (Web Text))

Max Activating Token Index: 142