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

Dataset: Open Web Text

Neuron 224 in Layer 2

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: 4.9212. Min Range: -4.9212

Max Act: 4.9212. Min Act: -0.1700

Data Index: 382252 (Open Web Text)

Max Activating Token Index: 13

Text #1

Max Range: 4.9212. Min Range: -4.9212

Max Act: 4.8635. Min Act: -0.1700

Data Index: 7015177 (Open Web Text)

Max Activating Token Index: 750

Text #2

Max Range: 4.9212. Min Range: -4.9212

Max Act: 4.8437. Min Act: -0.1700

Data Index: 295849 (Open Web Text)

Max Activating Token Index: 914

Text #3

Max Range: 4.9212. Min Range: -4.9212

Max Act: 4.6866. Min Act: -0.1700

Data Index: 3709403 (Open Web Text)

Max Activating Token Index: 22

Text #4

Max Range: 4.9212. Min Range: -4.9212

Max Act: 4.6568. Min Act: -0.1700

Data Index: 8800674 (Open Web Text)

Max Activating Token Index: 23

Text #5

Max Range: 4.9212. Min Range: -4.9212

Max Act: 4.6014. Min Act: -0.1700

Data Index: 1196068 (Open Web Text)

Max Activating Token Index: 520

Text #6

Max Range: 4.9212. Min Range: -4.9212

Max Act: 4.6337. Min Act: -0.1700

Data Index: 4697876 (Open Web Text)

Max Activating Token Index: 11

Text #7

Max Range: 4.9212. Min Range: -4.9212

Max Act: 4.5998. Min Act: -0.1700

Data Index: 7777130 (Open Web Text)

Max Activating Token Index: 281

Text #8

Max Range: 4.9212. Min Range: -4.9212

Max Act: 4.5607. Min Act: -0.1700

Data Index: 6844719 (Open Web Text)

Max Activating Token Index: 736

Text #9

Max Range: 4.9212. Min Range: -4.9212

Max Act: 4.5551. Min Act: -0.1700

Data Index: 34722 (Open Web Text)

Max Activating Token Index: 16

Text #10

Max Range: 4.9212. Min Range: -4.9212

Max Act: 4.5812. Min Act: -0.1700

Data Index: 2171345 (Open Web Text)

Max Activating Token Index: 272

Text #11

Max Range: 4.9212. Min Range: -4.9212

Max Act: 4.5567. Min Act: -0.1700

Data Index: 5399671 (Open Web Text)

Max Activating Token Index: 13

Text #12

Max Range: 4.9212. Min Range: -4.9212

Max Act: 4.5858. Min Act: -0.1700

Data Index: 7214145 (Open Web Text)

Max Activating Token Index: 513

Text #13

Max Range: 4.9212. Min Range: -4.9212

Max Act: 4.5471. Min Act: -0.1700

Data Index: 7771912 (Open Web Text)

Max Activating Token Index: 58

Text #14

Max Range: 4.9212. Min Range: -4.9212

Max Act: 4.5121. Min Act: -0.1700

Data Index: 1728717 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 4.9212. Min Range: -4.9212

Max Act: 4.4944. Min Act: -0.1700

Data Index: 5742696 (Open Web Text)

Max Activating Token Index: 16

Text #16

Max Range: 4.9212. Min Range: -4.9212

Max Act: 4.4915. Min Act: -0.1700

Data Index: 1360060 (Open Web Text)

Max Activating Token Index: 1006

Text #17

Max Range: 4.9212. Min Range: -4.9212

Max Act: 4.4673. Min Act: -0.1700

Data Index: 2072087 (Open Web Text)

Max Activating Token Index: 190

Text #18

Max Range: 4.9212. Min Range: -4.9212

Max Act: 4.4589. Min Act: -0.1700

Data Index: 2437298 (Open Web Text)

Max Activating Token Index: 46

Text #19

Max Range: 4.9212. Min Range: -4.9212

Max Act: 4.4712. Min Act: -0.1700

Data Index: 5939221 (Open Web Text)

Max Activating Token Index: 113