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

Dataset: Open Web Text

Neuron 464 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: 4.1823. Min Range: -4.1823

Max Act: 4.1794. Min Act: -0.1700

Data Index: 4629274 (Open Web Text)

Max Activating Token Index: 422

Text #1

Max Range: 4.1823. Min Range: -4.1823

Max Act: 4.1823. Min Act: -0.1700

Data Index: 3445154 (Open Web Text)

Max Activating Token Index: 264

Text #2

Max Range: 4.1823. Min Range: -4.1823

Max Act: 4.1590. Min Act: -0.1700

Data Index: 989152 (Open Web Text)

Max Activating Token Index: 797

Text #3

Max Range: 4.1823. Min Range: -4.1823

Max Act: 4.1080. Min Act: -0.1700

Data Index: 3520415 (Open Web Text)

Max Activating Token Index: 137

Text #4

Max Range: 4.1823. Min Range: -4.1823

Max Act: 4.0701. Min Act: -0.1700

Data Index: 1683145 (Open Web Text)

Max Activating Token Index: 86

Text #5

Max Range: 4.1823. Min Range: -4.1823

Max Act: 4.0776. Min Act: -0.1700

Data Index: 4897426 (Open Web Text)

Max Activating Token Index: 698

Text #6

Max Range: 4.1823. Min Range: -4.1823

Max Act: 4.0882. Min Act: -0.1700

Data Index: 7699005 (Open Web Text)

Max Activating Token Index: 215

Text #7

Max Range: 4.1823. Min Range: -4.1823

Max Act: 4.1002. Min Act: -0.1700

Data Index: 8442492 (Open Web Text)

Max Activating Token Index: 640

Text #8

Max Range: 4.1823. Min Range: -4.1823

Max Act: 4.0652. Min Act: -0.1700

Data Index: 4767662 (Open Web Text)

Max Activating Token Index: 179

Text #9

Max Range: 4.1823. Min Range: -4.1823

Max Act: 4.0469. Min Act: -0.1700

Data Index: 5351595 (Open Web Text)

Max Activating Token Index: 1000

Text #10

Max Range: 4.1823. Min Range: -4.1823

Max Act: 4.0403. Min Act: -0.1700

Data Index: 7904432 (Open Web Text)

Max Activating Token Index: 180

Text #11

Max Range: 4.1823. Min Range: -4.1823

Max Act: 4.0656. Min Act: -0.1700

Data Index: 1154628 (Open Web Text)

Max Activating Token Index: 445

Text #12

Max Range: 4.1823. Min Range: -4.1823

Max Act: 4.0601. Min Act: -0.1700

Data Index: 6683009 (Open Web Text)

Max Activating Token Index: 10

Text #13

Max Range: 4.1823. Min Range: -4.1823

Max Act: 4.0163. Min Act: -0.1700

Data Index: 5046752 (Open Web Text)

Max Activating Token Index: 107

Text #14

Max Range: 4.1823. Min Range: -4.1823

Max Act: 4.0188. Min Act: -0.1700

Data Index: 5435771 (Open Web Text)

Max Activating Token Index: 616

Text #15

Max Range: 4.1823. Min Range: -4.1823

Max Act: 4.0069. Min Act: -0.1700

Data Index: 2241308 (Open Web Text)

Max Activating Token Index: 282

Text #16

Max Range: 4.1823. Min Range: -4.1823

Max Act: 4.0196. Min Act: -0.1700

Data Index: 3553433 (Open Web Text)

Max Activating Token Index: 97

Text #17

Max Range: 4.1823. Min Range: -4.1823

Max Act: 4.0412. Min Act: -0.1700

Data Index: 5789925 (Open Web Text)

Max Activating Token Index: 456

Text #18

Max Range: 4.1823. Min Range: -4.1823

Max Act: 4.0274. Min Act: -0.1700

Data Index: 1586018 (Open Web Text)

Max Activating Token Index: 539

Text #19

Max Range: 4.1823. Min Range: -4.1823

Max Act: 4.0207. Min Act: -0.1700

Data Index: 1671953 (Open Web Text)

Max Activating Token Index: 802