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

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

Neuron 5169 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3808. Min Range: -4.3808

Max Act: 4.3084. Min Act: -0.0000

Data Index: 827522 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 4.3808. Min Range: -4.3808

Max Act: 4.2238. Min Act: -0.0000

Data Index: 1230798 (C4 (Web Text))

Max Activating Token Index: 49

Text #2

Max Range: 4.3808. Min Range: -4.3808

Max Act: 4.3808. Min Act: -0.0000

Data Index: 766896 (C4 (Web Text))

Max Activating Token Index: 217

Text #3

Max Range: 4.3808. Min Range: -4.3808

Max Act: 3.9876. Min Act: -0.0000

Data Index: 623826 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 4.3808. Min Range: -4.3808

Max Act: 4.0052. Min Act: -0.0000

Data Index: 430815 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 4.3808. Min Range: -4.3808

Max Act: 3.6437. Min Act: -0.0000

Data Index: 52852 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 4.3808. Min Range: -4.3808

Max Act: 3.5150. Min Act: -0.0000

Data Index: 123876 (C4 (Web Text))

Max Activating Token Index: 143

Text #7

Max Range: 4.3808. Min Range: -4.3808

Max Act: 3.6927. Min Act: -0.0000

Data Index: 670079 (C4 (Web Text))

Max Activating Token Index: 1017

Text #8

Max Range: 4.3808. Min Range: -4.3808

Max Act: 3.1542. Min Act: -0.0000

Data Index: 203463 (C4 (Web Text))

Max Activating Token Index: 382

Text #9

Max Range: 4.3808. Min Range: -4.3808

Max Act: 3.4126. Min Act: -0.0000

Data Index: 579515 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 4.3808. Min Range: -4.3808

Max Act: 3.2686. Min Act: -0.0000

Data Index: 47619 (C4 (Web Text))

Max Activating Token Index: 662

Text #11

Max Range: 4.3808. Min Range: -4.3808

Max Act: 3.0225. Min Act: -0.0000

Data Index: 581714 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 4.3808. Min Range: -4.3808

Max Act: 3.1015. Min Act: -0.0000

Data Index: 453692 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 4.3808. Min Range: -4.3808

Max Act: 3.0148. Min Act: -0.0000

Data Index: 339897 (C4 (Web Text))

Max Activating Token Index: 350

Text #14

Max Range: 4.3808. Min Range: -4.3808

Max Act: 3.0059. Min Act: -0.0000

Data Index: 809752 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 4.3808. Min Range: -4.3808

Max Act: 3.0041. Min Act: -0.0000

Data Index: 50747 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 4.3808. Min Range: -4.3808

Max Act: 2.9933. Min Act: -0.0000

Data Index: 277076 (C4 (Web Text))

Max Activating Token Index: 561

Text #17

Max Range: 4.3808. Min Range: -4.3808

Max Act: 2.9759. Min Act: -0.0000

Data Index: 913638 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 4.3808. Min Range: -4.3808

Max Act: 2.9200. Min Act: -0.0000

Data Index: 104526 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 4.3808. Min Range: -4.3808

Max Act: 2.8705. Min Act: -0.0000

Data Index: 1345087 (C4 (Web Text))

Max Activating Token Index: 724