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

Dataset: Open Web Text

Neuron 2212 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: 3.9099. Min Range: -3.9099

Max Act: 3.8687. Min Act: -0.1700

Data Index: 1738643 (Open Web Text)

Max Activating Token Index: 154

Text #1

Max Range: 3.9099. Min Range: -3.9099

Max Act: 3.9099. Min Act: -0.1700

Data Index: 6981717 (Open Web Text)

Max Activating Token Index: 46

Text #2

Max Range: 3.9099. Min Range: -3.9099

Max Act: 3.7889. Min Act: -0.1700

Data Index: 1738647 (Open Web Text)

Max Activating Token Index: 10

Text #3

Max Range: 3.9099. Min Range: -3.9099

Max Act: 3.8234. Min Act: -0.1700

Data Index: 731471 (Open Web Text)

Max Activating Token Index: 531

Text #4

Max Range: 3.9099. Min Range: -3.9099

Max Act: 3.7772. Min Act: -0.1700

Data Index: 6981716 (Open Web Text)

Max Activating Token Index: 993

Text #5

Max Range: 3.9099. Min Range: -3.9099

Max Act: 3.7537. Min Act: -0.1700

Data Index: 7364548 (Open Web Text)

Max Activating Token Index: 52

Text #6

Max Range: 3.9099. Min Range: -3.9099

Max Act: 3.7917. Min Act: -0.1700

Data Index: 5015588 (Open Web Text)

Max Activating Token Index: 405

Text #7

Max Range: 3.9099. Min Range: -3.9099

Max Act: 3.7551. Min Act: -0.1700

Data Index: 4968777 (Open Web Text)

Max Activating Token Index: 152

Text #8

Max Range: 3.9099. Min Range: -3.9099

Max Act: 3.7522. Min Act: -0.1700

Data Index: 2165408 (Open Web Text)

Max Activating Token Index: 516

Text #9

Max Range: 3.9099. Min Range: -3.9099

Max Act: 3.7445. Min Act: -0.1700

Data Index: 1025173 (Open Web Text)

Max Activating Token Index: 511

Text #10

Max Range: 3.9099. Min Range: -3.9099

Max Act: 3.7204. Min Act: -0.1700

Data Index: 1738646 (Open Web Text)

Max Activating Token Index: 282

Text #11

Max Range: 3.9099. Min Range: -3.9099

Max Act: 3.6962. Min Act: -0.1700

Data Index: 2222537 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.9099. Min Range: -3.9099

Max Act: 3.6515. Min Act: -0.1700

Data Index: 2099546 (Open Web Text)

Max Activating Token Index: 240

Text #13

Max Range: 3.9099. Min Range: -3.9099

Max Act: 3.6250. Min Act: -0.1700

Data Index: 6908838 (Open Web Text)

Max Activating Token Index: 320

Text #14

Max Range: 3.9099. Min Range: -3.9099

Max Act: 3.6419. Min Act: -0.1700

Data Index: 349857 (Open Web Text)

Max Activating Token Index: 595

Text #15

Max Range: 3.9099. Min Range: -3.9099

Max Act: 3.6479. Min Act: -0.1700

Data Index: 1738638 (Open Web Text)

Max Activating Token Index: 62

Text #16

Max Range: 3.9099. Min Range: -3.9099

Max Act: 3.6282. Min Act: -0.1700

Data Index: 5197423 (Open Web Text)

Max Activating Token Index: 49

Text #17

Max Range: 3.9099. Min Range: -3.9099

Max Act: 3.6082. Min Act: -0.1700

Data Index: 1714576 (Open Web Text)

Max Activating Token Index: 570

Text #18

Max Range: 3.9099. Min Range: -3.9099

Max Act: 3.6184. Min Act: -0.1700

Data Index: 6213566 (Open Web Text)

Max Activating Token Index: 350

Text #19

Max Range: 3.9099. Min Range: -3.9099

Max Act: 3.5918. Min Act: -0.1700

Data Index: 6783517 (Open Web Text)

Max Activating Token Index: 888