Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 100 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.8500. Min Act: -0.1700

Data Index: 6615889 (Open Web Text)

Max Activating Token Index: 11

Text #1

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.8420. Min Act: -0.1700

Data Index: 442024 (Open Web Text)

Max Activating Token Index: 23

Text #2

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.8438. Min Act: -0.1700

Data Index: 6574108 (Open Web Text)

Max Activating Token Index: 578

Text #3

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.8030. Min Act: -0.1700

Data Index: 3169199 (Open Web Text)

Max Activating Token Index: 985

Text #4

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.7838. Min Act: -0.1700

Data Index: 2015110 (Open Web Text)

Max Activating Token Index: 31

Text #5

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.7790. Min Act: -0.1700

Data Index: 6974637 (Open Web Text)

Max Activating Token Index: 85

Text #6

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.7454. Min Act: -0.1700

Data Index: 5139881 (Open Web Text)

Max Activating Token Index: 28

Text #7

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.7280. Min Act: -0.1700

Data Index: 3369014 (Open Web Text)

Max Activating Token Index: 18

Text #8

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.7238. Min Act: -0.1700

Data Index: 5745408 (Open Web Text)

Max Activating Token Index: 101

Text #9

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.7304. Min Act: -0.1700

Data Index: 7179789 (Open Web Text)

Max Activating Token Index: 691

Text #10

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.7411. Min Act: -0.1700

Data Index: 4472009 (Open Web Text)

Max Activating Token Index: 474

Text #11

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.6828. Min Act: -0.1700

Data Index: 4774409 (Open Web Text)

Max Activating Token Index: 24

Text #12

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.6646. Min Act: -0.1700

Data Index: 668332 (Open Web Text)

Max Activating Token Index: 107

Text #13

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.7161. Min Act: -0.1700

Data Index: 5202356 (Open Web Text)

Max Activating Token Index: 186

Text #14

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.6913. Min Act: -0.1700

Data Index: 5629676 (Open Web Text)

Max Activating Token Index: 845

Text #15

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.6978. Min Act: -0.1700

Data Index: 2283731 (Open Web Text)

Max Activating Token Index: 695

Text #16

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.6914. Min Act: -0.1700

Data Index: 2289907 (Open Web Text)

Max Activating Token Index: 855

Text #17

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.6865. Min Act: -0.1700

Data Index: 6222804 (Open Web Text)

Max Activating Token Index: 118

Text #18

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.7225. Min Act: -0.1700

Data Index: 6352072 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.6891. Min Act: -0.1700

Data Index: 4008353 (Open Web Text)

Max Activating Token Index: 699