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

Dataset: Open Web Text

Neuron 1009 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: 1.7508. Min Range: -1.7508

Max Act: 1.7508. Min Act: -0.1700

Data Index: 4400780 (Open Web Text)

Max Activating Token Index: 408

Text #1

Max Range: 1.7508. Min Range: -1.7508

Max Act: 1.7442. Min Act: -0.1700

Data Index: 7488313 (Open Web Text)

Max Activating Token Index: 750

Text #2

Max Range: 1.7508. Min Range: -1.7508

Max Act: 1.7001. Min Act: -0.1700

Data Index: 1182466 (Open Web Text)

Max Activating Token Index: 194

Text #3

Max Range: 1.7508. Min Range: -1.7508

Max Act: 1.7076. Min Act: -0.1700

Data Index: 7529931 (Open Web Text)

Max Activating Token Index: 563

Text #4

Max Range: 1.7508. Min Range: -1.7508

Max Act: 1.6733. Min Act: -0.1700

Data Index: 5620159 (Open Web Text)

Max Activating Token Index: 704

Text #5

Max Range: 1.7508. Min Range: -1.7508

Max Act: 1.6616. Min Act: -0.1700

Data Index: 2434722 (Open Web Text)

Max Activating Token Index: 812

Text #6

Max Range: 1.7508. Min Range: -1.7508

Max Act: 1.6496. Min Act: -0.1700

Data Index: 7686613 (Open Web Text)

Max Activating Token Index: 165

Text #7

Max Range: 1.7508. Min Range: -1.7508

Max Act: 1.6503. Min Act: -0.1700

Data Index: 3447446 (Open Web Text)

Max Activating Token Index: 365

Text #8

Max Range: 1.7508. Min Range: -1.7508

Max Act: 1.6498. Min Act: -0.1700

Data Index: 4953250 (Open Web Text)

Max Activating Token Index: 253

Text #9

Max Range: 1.7508. Min Range: -1.7508

Max Act: 1.6624. Min Act: -0.1700

Data Index: 4851921 (Open Web Text)

Max Activating Token Index: 275

Text #10

Max Range: 1.7508. Min Range: -1.7508

Max Act: 1.6525. Min Act: -0.1700

Data Index: 7163504 (Open Web Text)

Max Activating Token Index: 231

Text #11

Max Range: 1.7508. Min Range: -1.7508

Max Act: 1.6529. Min Act: -0.1700

Data Index: 748588 (Open Web Text)

Max Activating Token Index: 497

Text #12

Max Range: 1.7508. Min Range: -1.7508

Max Act: 1.6361. Min Act: -0.1700

Data Index: 8516565 (Open Web Text)

Max Activating Token Index: 205

Text #13

Max Range: 1.7508. Min Range: -1.7508

Max Act: 1.6616. Min Act: -0.1700

Data Index: 6917245 (Open Web Text)

Max Activating Token Index: 463

Text #14

Max Range: 1.7508. Min Range: -1.7508

Max Act: 1.6354. Min Act: -0.1700

Data Index: 6166442 (Open Web Text)

Max Activating Token Index: 39

Text #15

Max Range: 1.7508. Min Range: -1.7508

Max Act: 1.6148. Min Act: -0.1700

Data Index: 694712 (Open Web Text)

Max Activating Token Index: 805

Text #16

Max Range: 1.7508. Min Range: -1.7508

Max Act: 1.6370. Min Act: -0.1700

Data Index: 4315224 (Open Web Text)

Max Activating Token Index: 745

Text #17

Max Range: 1.7508. Min Range: -1.7508

Max Act: 1.6350. Min Act: -0.1700

Data Index: 4199671 (Open Web Text)

Max Activating Token Index: 862

Text #18

Max Range: 1.7508. Min Range: -1.7508

Max Act: 1.6325. Min Act: -0.1700

Data Index: 4231212 (Open Web Text)

Max Activating Token Index: 904

Text #19

Max Range: 1.7508. Min Range: -1.7508

Max Act: 1.6283. Min Act: -0.1700

Data Index: 3583521 (Open Web Text)

Max Activating Token Index: 264