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

Dataset: Open Web Text

Neuron 77 in Layer 4

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: 3.2319. Min Range: -3.2319

Max Act: 3.2319. Min Act: -0.1700

Data Index: 5902923 (Open Web Text)

Max Activating Token Index: 431

Text #1

Max Range: 3.2319. Min Range: -3.2319

Max Act: 3.1509. Min Act: -0.1700

Data Index: 1452892 (Open Web Text)

Max Activating Token Index: 823

Text #2

Max Range: 3.2319. Min Range: -3.2319

Max Act: 3.2064. Min Act: -0.1700

Data Index: 5665999 (Open Web Text)

Max Activating Token Index: 933

Text #3

Max Range: 3.2319. Min Range: -3.2319

Max Act: 3.1394. Min Act: -0.1700

Data Index: 1212160 (Open Web Text)

Max Activating Token Index: 489

Text #4

Max Range: 3.2319. Min Range: -3.2319

Max Act: 3.1245. Min Act: -0.1700

Data Index: 5320568 (Open Web Text)

Max Activating Token Index: 1002

Text #5

Max Range: 3.2319. Min Range: -3.2319

Max Act: 3.1508. Min Act: -0.1700

Data Index: 1212171 (Open Web Text)

Max Activating Token Index: 517

Text #6

Max Range: 3.2319. Min Range: -3.2319

Max Act: 3.1226. Min Act: -0.1700

Data Index: 4636679 (Open Web Text)

Max Activating Token Index: 371

Text #7

Max Range: 3.2319. Min Range: -3.2319

Max Act: 3.1174. Min Act: -0.1700

Data Index: 8564009 (Open Web Text)

Max Activating Token Index: 525

Text #8

Max Range: 3.2319. Min Range: -3.2319

Max Act: 3.1081. Min Act: -0.1700

Data Index: 3370884 (Open Web Text)

Max Activating Token Index: 327

Text #9

Max Range: 3.2319. Min Range: -3.2319

Max Act: 3.1125. Min Act: -0.1700

Data Index: 2797040 (Open Web Text)

Max Activating Token Index: 659

Text #10

Max Range: 3.2319. Min Range: -3.2319

Max Act: 3.0784. Min Act: -0.1700

Data Index: 2197598 (Open Web Text)

Max Activating Token Index: 771

Text #11

Max Range: 3.2319. Min Range: -3.2319

Max Act: 3.0657. Min Act: -0.1700

Data Index: 3845455 (Open Web Text)

Max Activating Token Index: 417

Text #12

Max Range: 3.2319. Min Range: -3.2319

Max Act: 3.0929. Min Act: -0.1700

Data Index: 8243855 (Open Web Text)

Max Activating Token Index: 818

Text #13

Max Range: 3.2319. Min Range: -3.2319

Max Act: 3.0811. Min Act: -0.1700

Data Index: 6675742 (Open Web Text)

Max Activating Token Index: 140

Text #14

Max Range: 3.2319. Min Range: -3.2319

Max Act: 3.0505. Min Act: -0.1700

Data Index: 2308962 (Open Web Text)

Max Activating Token Index: 989

Text #15

Max Range: 3.2319. Min Range: -3.2319

Max Act: 3.0589. Min Act: -0.1700

Data Index: 8436457 (Open Web Text)

Max Activating Token Index: 653

Text #16

Max Range: 3.2319. Min Range: -3.2319

Max Act: 3.0666. Min Act: -0.1700

Data Index: 7804642 (Open Web Text)

Max Activating Token Index: 568

Text #17

Max Range: 3.2319. Min Range: -3.2319

Max Act: 3.0633. Min Act: -0.1700

Data Index: 1216904 (Open Web Text)

Max Activating Token Index: 36

Text #18

Max Range: 3.2319. Min Range: -3.2319

Max Act: 3.0422. Min Act: -0.1700

Data Index: 322386 (Open Web Text)

Max Activating Token Index: 148

Text #19

Max Range: 3.2319. Min Range: -3.2319

Max Act: 3.0475. Min Act: -0.1700

Data Index: 4441588 (Open Web Text)

Max Activating Token Index: 635