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

Dataset: Open Web Text

Neuron 1692 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: 1.5591. Min Range: -1.5591

Max Act: 1.5591. Min Act: -0.1479

Data Index: 1458387 (Open Web Text)

Max Activating Token Index: 495

Text #1

Max Range: 1.5591. Min Range: -1.5591

Max Act: 1.5562. Min Act: -0.1698

Data Index: 3264257 (Open Web Text)

Max Activating Token Index: 97

Text #2

Max Range: 1.5591. Min Range: -1.5591

Max Act: 1.5558. Min Act: -0.1486

Data Index: 7603800 (Open Web Text)

Max Activating Token Index: 463

Text #3

Max Range: 1.5591. Min Range: -1.5591

Max Act: 1.5422. Min Act: -0.1423

Data Index: 6583292 (Open Web Text)

Max Activating Token Index: 638

Text #4

Max Range: 1.5591. Min Range: -1.5591

Max Act: 1.5510. Min Act: -0.1662

Data Index: 2767155 (Open Web Text)

Max Activating Token Index: 278

Text #5

Max Range: 1.5591. Min Range: -1.5591

Max Act: 1.5446. Min Act: -0.1659

Data Index: 7428822 (Open Web Text)

Max Activating Token Index: 622

Text #6

Max Range: 1.5591. Min Range: -1.5591

Max Act: 1.5366. Min Act: -0.1693

Data Index: 5344344 (Open Web Text)

Max Activating Token Index: 274

Text #7

Max Range: 1.5591. Min Range: -1.5591

Max Act: 1.5383. Min Act: -0.1609

Data Index: 89682 (Open Web Text)

Max Activating Token Index: 91

Text #8

Max Range: 1.5591. Min Range: -1.5591

Max Act: 1.5297. Min Act: -0.1652

Data Index: 650856 (Open Web Text)

Max Activating Token Index: 581

Text #9

Max Range: 1.5591. Min Range: -1.5591

Max Act: 1.5432. Min Act: -0.1675

Data Index: 1187486 (Open Web Text)

Max Activating Token Index: 93

Text #10

Max Range: 1.5591. Min Range: -1.5591

Max Act: 1.5493. Min Act: -0.1579

Data Index: 5274905 (Open Web Text)

Max Activating Token Index: 599

Text #11

Max Range: 1.5591. Min Range: -1.5591

Max Act: 1.5254. Min Act: -0.1675

Data Index: 3010869 (Open Web Text)

Max Activating Token Index: 385

Text #12

Max Range: 1.5591. Min Range: -1.5591

Max Act: 1.5301. Min Act: -0.1557

Data Index: 5661510 (Open Web Text)

Max Activating Token Index: 97

Text #13

Max Range: 1.5591. Min Range: -1.5591

Max Act: 1.5327. Min Act: -0.1665

Data Index: 2707250 (Open Web Text)

Max Activating Token Index: 654

Text #14

Max Range: 1.5591. Min Range: -1.5591

Max Act: 1.5015. Min Act: -0.1698

Data Index: 2043978 (Open Web Text)

Max Activating Token Index: 435

Text #15

Max Range: 1.5591. Min Range: -1.5591

Max Act: 1.5205. Min Act: -0.1118

Data Index: 994780 (Open Web Text)

Max Activating Token Index: 148

Text #16

Max Range: 1.5591. Min Range: -1.5591

Max Act: 1.5086. Min Act: -0.1357

Data Index: 7899001 (Open Web Text)

Max Activating Token Index: 274

Text #17

Max Range: 1.5591. Min Range: -1.5591

Max Act: 1.5140. Min Act: -0.1673

Data Index: 4791600 (Open Web Text)

Max Activating Token Index: 736

Text #18

Max Range: 1.5591. Min Range: -1.5591

Max Act: 1.5125. Min Act: -0.1689

Data Index: 5968311 (Open Web Text)

Max Activating Token Index: 192

Text #19

Max Range: 1.5591. Min Range: -1.5591

Max Act: 1.5033. Min Act: -0.1649

Data Index: 5661509 (Open Web Text)

Max Activating Token Index: 425