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

Dataset: Open Web Text

Neuron 1752 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: 5.0823. Min Range: -5.0823

Max Act: 5.0778. Min Act: -0.1700

Data Index: 6700479 (Open Web Text)

Max Activating Token Index: 395

Text #1

Max Range: 5.0823. Min Range: -5.0823

Max Act: 5.0823. Min Act: -0.1700

Data Index: 8659685 (Open Web Text)

Max Activating Token Index: 711

Text #2

Max Range: 5.0823. Min Range: -5.0823

Max Act: 5.0720. Min Act: -0.1700

Data Index: 6570971 (Open Web Text)

Max Activating Token Index: 82

Text #3

Max Range: 5.0823. Min Range: -5.0823

Max Act: 5.0371. Min Act: -0.1700

Data Index: 1180535 (Open Web Text)

Max Activating Token Index: 383

Text #4

Max Range: 5.0823. Min Range: -5.0823

Max Act: 5.0280. Min Act: -0.1700

Data Index: 966839 (Open Web Text)

Max Activating Token Index: 669

Text #5

Max Range: 5.0823. Min Range: -5.0823

Max Act: 5.0089. Min Act: -0.1700

Data Index: 3698529 (Open Web Text)

Max Activating Token Index: 445

Text #6

Max Range: 5.0823. Min Range: -5.0823

Max Act: 4.9583. Min Act: -0.1700

Data Index: 4591736 (Open Web Text)

Max Activating Token Index: 14

Text #7

Max Range: 5.0823. Min Range: -5.0823

Max Act: 4.9476. Min Act: -0.1700

Data Index: 1811894 (Open Web Text)

Max Activating Token Index: 24

Text #8

Max Range: 5.0823. Min Range: -5.0823

Max Act: 4.9377. Min Act: -0.1700

Data Index: 6481216 (Open Web Text)

Max Activating Token Index: 830

Text #9

Max Range: 5.0823. Min Range: -5.0823

Max Act: 4.8827. Min Act: -0.1700

Data Index: 1645560 (Open Web Text)

Max Activating Token Index: 587

Text #10

Max Range: 5.0823. Min Range: -5.0823

Max Act: 4.8809. Min Act: -0.1700

Data Index: 2774256 (Open Web Text)

Max Activating Token Index: 219

Text #11

Max Range: 5.0823. Min Range: -5.0823

Max Act: 4.9026. Min Act: -0.1700

Data Index: 2149752 (Open Web Text)

Max Activating Token Index: 733

Text #12

Max Range: 5.0823. Min Range: -5.0823

Max Act: 4.9271. Min Act: -0.1700

Data Index: 4815899 (Open Web Text)

Max Activating Token Index: 810

Text #13

Max Range: 5.0823. Min Range: -5.0823

Max Act: 4.9200. Min Act: -0.1700

Data Index: 5382163 (Open Web Text)

Max Activating Token Index: 32

Text #14

Max Range: 5.0823. Min Range: -5.0823

Max Act: 4.8568. Min Act: -0.1700

Data Index: 668248 (Open Web Text)

Max Activating Token Index: 584

Text #15

Max Range: 5.0823. Min Range: -5.0823

Max Act: 4.8864. Min Act: -0.1700

Data Index: 6017182 (Open Web Text)

Max Activating Token Index: 639

Text #16

Max Range: 5.0823. Min Range: -5.0823

Max Act: 4.8447. Min Act: -0.1700

Data Index: 2426574 (Open Web Text)

Max Activating Token Index: 109

Text #17

Max Range: 5.0823. Min Range: -5.0823

Max Act: 4.8416. Min Act: -0.1700

Data Index: 861664 (Open Web Text)

Max Activating Token Index: 728

Text #18

Max Range: 5.0823. Min Range: -5.0823

Max Act: 4.8363. Min Act: -0.1700

Data Index: 5598549 (Open Web Text)

Max Activating Token Index: 1015

Text #19

Max Range: 5.0823. Min Range: -5.0823

Max Act: 4.8487. Min Act: -0.1700

Data Index: 5369809 (Open Web Text)

Max Activating Token Index: 248