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

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

Neuron 916 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.5051. Min Act: -0.0001

Data Index: 386608 (C4 (Web Text))

Max Activating Token Index: 171

Text #1

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.4919. Min Act: -0.0001

Data Index: 55967 (C4 (Web Text))

Max Activating Token Index: 1001

Text #2

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.4842. Min Act: -0.0001

Data Index: 853148 (C4 (Web Text))

Max Activating Token Index: 137

Text #3

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.5184. Min Act: -0.0001

Data Index: 1109057 (C4 (Web Text))

Max Activating Token Index: 600

Text #4

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.3857. Min Act: -0.0001

Data Index: 1079397 (C4 (Web Text))

Max Activating Token Index: 818

Text #5

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.3587. Min Act: -0.0001

Data Index: 958388 (C4 (Web Text))

Max Activating Token Index: 533

Text #6

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.3747. Min Act: -0.0001

Data Index: 808212 (C4 (Web Text))

Max Activating Token Index: 1012

Text #7

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.3929. Min Act: -0.0001

Data Index: 974808 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.3772. Min Act: -0.0001

Data Index: 277540 (C4 (Web Text))

Max Activating Token Index: 658

Text #9

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.3912. Min Act: -0.0001

Data Index: 401638 (C4 (Web Text))

Max Activating Token Index: 788

Text #10

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.3847. Min Act: -0.0001

Data Index: 416717 (C4 (Web Text))

Max Activating Token Index: 183

Text #11

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.3663. Min Act: -0.0001

Data Index: 1327506 (C4 (Web Text))

Max Activating Token Index: 821

Text #12

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.3760. Min Act: -0.0001

Data Index: 613202 (C4 (Web Text))

Max Activating Token Index: 852

Text #13

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.3628. Min Act: -0.0001

Data Index: 906194 (C4 (Web Text))

Max Activating Token Index: 950

Text #14

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.3725. Min Act: -0.0001

Data Index: 1344914 (C4 (Web Text))

Max Activating Token Index: 445

Text #15

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.3753. Min Act: -0.0001

Data Index: 1238559 (C4 (Web Text))

Max Activating Token Index: 793

Text #16

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.3727. Min Act: -0.0001

Data Index: 176656 (C4 (Web Text))

Max Activating Token Index: 666

Text #17

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.3554. Min Act: -0.0001

Data Index: 340561 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.3796. Min Act: -0.0001

Data Index: 1249441 (C4 (Web Text))

Max Activating Token Index: 769

Text #19

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.3712. Min Act: -0.0001

Data Index: 980487 (C4 (Web Text))

Max Activating Token Index: 641