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

Dataset: Open Web Text

Neuron 140 in Layer 1

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: 3.1042. Min Range: -3.1042

Max Act: 3.1042. Min Act: -0.1700

Data Index: 7165411 (Open Web Text)

Max Activating Token Index: 393

Text #1

Max Range: 3.1042. Min Range: -3.1042

Max Act: 3.0578. Min Act: -0.1700

Data Index: 3010698 (Open Web Text)

Max Activating Token Index: 1015

Text #2

Max Range: 3.1042. Min Range: -3.1042

Max Act: 3.0562. Min Act: -0.1700

Data Index: 8207893 (Open Web Text)

Max Activating Token Index: 199

Text #3

Max Range: 3.1042. Min Range: -3.1042

Max Act: 3.0332. Min Act: -0.1700

Data Index: 8128921 (Open Web Text)

Max Activating Token Index: 1004

Text #4

Max Range: 3.1042. Min Range: -3.1042

Max Act: 3.0366. Min Act: -0.1700

Data Index: 8560254 (Open Web Text)

Max Activating Token Index: 781

Text #5

Max Range: 3.1042. Min Range: -3.1042

Max Act: 3.0315. Min Act: -0.1662

Data Index: 8484859 (Open Web Text)

Max Activating Token Index: 861

Text #6

Max Range: 3.1042. Min Range: -3.1042

Max Act: 3.0144. Min Act: -0.1697

Data Index: 8560243 (Open Web Text)

Max Activating Token Index: 539

Text #7

Max Range: 3.1042. Min Range: -3.1042

Max Act: 3.0078. Min Act: -0.1699

Data Index: 4951645 (Open Web Text)

Max Activating Token Index: 927

Text #8

Max Range: 3.1042. Min Range: -3.1042

Max Act: 3.0145. Min Act: -0.1674

Data Index: 3010680 (Open Web Text)

Max Activating Token Index: 414

Text #9

Max Range: 3.1042. Min Range: -3.1042

Max Act: 3.0108. Min Act: -0.1695

Data Index: 4926820 (Open Web Text)

Max Activating Token Index: 498

Text #10

Max Range: 3.1042. Min Range: -3.1042

Max Act: 3.0073. Min Act: -0.1700

Data Index: 8128935 (Open Web Text)

Max Activating Token Index: 903

Text #11

Max Range: 3.1042. Min Range: -3.1042

Max Act: 3.0179. Min Act: -0.1700

Data Index: 373450 (Open Web Text)

Max Activating Token Index: 625

Text #12

Max Range: 3.1042. Min Range: -3.1042

Max Act: 2.9871. Min Act: -0.1684

Data Index: 4926797 (Open Web Text)

Max Activating Token Index: 582

Text #13

Max Range: 3.1042. Min Range: -3.1042

Max Act: 2.9949. Min Act: -0.1700

Data Index: 7165401 (Open Web Text)

Max Activating Token Index: 178

Text #14

Max Range: 3.1042. Min Range: -3.1042

Max Act: 2.9696. Min Act: -0.1678

Data Index: 8070613 (Open Web Text)

Max Activating Token Index: 562

Text #15

Max Range: 3.1042. Min Range: -3.1042

Max Act: 2.9788. Min Act: -0.1700

Data Index: 3010699 (Open Web Text)

Max Activating Token Index: 178

Text #16

Max Range: 3.1042. Min Range: -3.1042

Max Act: 2.9916. Min Act: -0.1698

Data Index: 1982585 (Open Web Text)

Max Activating Token Index: 527

Text #17

Max Range: 3.1042. Min Range: -3.1042

Max Act: 2.9601. Min Act: -0.1699

Data Index: 6366511 (Open Web Text)

Max Activating Token Index: 507

Text #18

Max Range: 3.1042. Min Range: -3.1042

Max Act: 2.9698. Min Act: -0.1694

Data Index: 6462426 (Open Web Text)

Max Activating Token Index: 935

Text #19

Max Range: 3.1042. Min Range: -3.1042

Max Act: 2.9626. Min Act: -0.1695

Data Index: 7783050 (Open Web Text)

Max Activating Token Index: 927