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

Dataset: Open Web Text

Neuron 1490 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: 3.9251. Min Range: -3.9251

Max Act: 3.9189. Min Act: -0.1700

Data Index: 2332694 (Open Web Text)

Max Activating Token Index: 600

Text #1

Max Range: 3.9251. Min Range: -3.9251

Max Act: 3.9178. Min Act: -0.1700

Data Index: 2332693 (Open Web Text)

Max Activating Token Index: 941

Text #2

Max Range: 3.9251. Min Range: -3.9251

Max Act: 3.8749. Min Act: -0.1700

Data Index: 8413460 (Open Web Text)

Max Activating Token Index: 695

Text #3

Max Range: 3.9251. Min Range: -3.9251

Max Act: 3.8953. Min Act: -0.1700

Data Index: 8776788 (Open Web Text)

Max Activating Token Index: 83

Text #4

Max Range: 3.9251. Min Range: -3.9251

Max Act: 3.9251. Min Act: -0.1700

Data Index: 8710116 (Open Web Text)

Max Activating Token Index: 1011

Text #5

Max Range: 3.9251. Min Range: -3.9251

Max Act: 3.8596. Min Act: -0.1700

Data Index: 3623040 (Open Web Text)

Max Activating Token Index: 605

Text #6

Max Range: 3.9251. Min Range: -3.9251

Max Act: 3.8081. Min Act: -0.1700

Data Index: 4054040 (Open Web Text)

Max Activating Token Index: 715

Text #7

Max Range: 3.9251. Min Range: -3.9251

Max Act: 3.8012. Min Act: -0.1700

Data Index: 77179 (Open Web Text)

Max Activating Token Index: 243

Text #8

Max Range: 3.9251. Min Range: -3.9251

Max Act: 3.7418. Min Act: -0.1700

Data Index: 8083977 (Open Web Text)

Max Activating Token Index: 988

Text #9

Max Range: 3.9251. Min Range: -3.9251

Max Act: 3.7637. Min Act: -0.1700

Data Index: 662716 (Open Web Text)

Max Activating Token Index: 396

Text #10

Max Range: 3.9251. Min Range: -3.9251

Max Act: 3.7934. Min Act: -0.1700

Data Index: 7607686 (Open Web Text)

Max Activating Token Index: 730

Text #11

Max Range: 3.9251. Min Range: -3.9251

Max Act: 3.7257. Min Act: -0.1700

Data Index: 1887563 (Open Web Text)

Max Activating Token Index: 430

Text #12

Max Range: 3.9251. Min Range: -3.9251

Max Act: 3.7361. Min Act: -0.1700

Data Index: 7915680 (Open Web Text)

Max Activating Token Index: 495

Text #13

Max Range: 3.9251. Min Range: -3.9251

Max Act: 3.6898. Min Act: -0.1700

Data Index: 7302681 (Open Web Text)

Max Activating Token Index: 231

Text #14

Max Range: 3.9251. Min Range: -3.9251

Max Act: 3.6699. Min Act: -0.1700

Data Index: 6050450 (Open Web Text)

Max Activating Token Index: 174

Text #15

Max Range: 3.9251. Min Range: -3.9251

Max Act: 3.7187. Min Act: -0.1700

Data Index: 5970257 (Open Web Text)

Max Activating Token Index: 1007

Text #16

Max Range: 3.9251. Min Range: -3.9251

Max Act: 3.6742. Min Act: -0.1700

Data Index: 555131 (Open Web Text)

Max Activating Token Index: 216

Text #17

Max Range: 3.9251. Min Range: -3.9251

Max Act: 3.6659. Min Act: -0.1700

Data Index: 5074942 (Open Web Text)

Max Activating Token Index: 332

Text #18

Max Range: 3.9251. Min Range: -3.9251

Max Act: 3.6655. Min Act: -0.1700

Data Index: 1201322 (Open Web Text)

Max Activating Token Index: 599

Text #19

Max Range: 3.9251. Min Range: -3.9251

Max Act: 3.6337. Min Act: -0.1700

Data Index: 4771438 (Open Web Text)

Max Activating Token Index: 423