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

Dataset: Open Web Text

Neuron 38 in Layer 5

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: 5.1995. Min Range: -5.1995

Max Act: 5.1995. Min Act: -0.1700

Data Index: 8177250 (Open Web Text)

Max Activating Token Index: 82

Text #1

Max Range: 5.1995. Min Range: -5.1995

Max Act: 5.1689. Min Act: -0.1700

Data Index: 7240330 (Open Web Text)

Max Activating Token Index: 631

Text #2

Max Range: 5.1995. Min Range: -5.1995

Max Act: 5.1519. Min Act: -0.1700

Data Index: 3331641 (Open Web Text)

Max Activating Token Index: 453

Text #3

Max Range: 5.1995. Min Range: -5.1995

Max Act: 5.0577. Min Act: -0.1700

Data Index: 690803 (Open Web Text)

Max Activating Token Index: 383

Text #4

Max Range: 5.1995. Min Range: -5.1995

Max Act: 4.9515. Min Act: -0.1700

Data Index: 2862362 (Open Web Text)

Max Activating Token Index: 539

Text #5

Max Range: 5.1995. Min Range: -5.1995

Max Act: 4.9679. Min Act: -0.1700

Data Index: 4914870 (Open Web Text)

Max Activating Token Index: 517

Text #6

Max Range: 5.1995. Min Range: -5.1995

Max Act: 4.9347. Min Act: -0.1700

Data Index: 621810 (Open Web Text)

Max Activating Token Index: 771

Text #7

Max Range: 5.1995. Min Range: -5.1995

Max Act: 4.9482. Min Act: -0.1700

Data Index: 8315287 (Open Web Text)

Max Activating Token Index: 700

Text #8

Max Range: 5.1995. Min Range: -5.1995

Max Act: 4.9379. Min Act: -0.1700

Data Index: 7791594 (Open Web Text)

Max Activating Token Index: 191

Text #9

Max Range: 5.1995. Min Range: -5.1995

Max Act: 4.8848. Min Act: -0.1700

Data Index: 2254060 (Open Web Text)

Max Activating Token Index: 144

Text #10

Max Range: 5.1995. Min Range: -5.1995

Max Act: 4.8684. Min Act: -0.1700

Data Index: 4659813 (Open Web Text)

Max Activating Token Index: 151

Text #11

Max Range: 5.1995. Min Range: -5.1995

Max Act: 4.8806. Min Act: -0.1700

Data Index: 378716 (Open Web Text)

Max Activating Token Index: 704

Text #12

Max Range: 5.1995. Min Range: -5.1995

Max Act: 4.8166. Min Act: -0.1700

Data Index: 4948782 (Open Web Text)

Max Activating Token Index: 150

Text #13

Max Range: 5.1995. Min Range: -5.1995

Max Act: 4.7333. Min Act: -0.1700

Data Index: 5095431 (Open Web Text)

Max Activating Token Index: 432

Text #14

Max Range: 5.1995. Min Range: -5.1995

Max Act: 4.7483. Min Act: -0.1700

Data Index: 419693 (Open Web Text)

Max Activating Token Index: 525

Text #15

Max Range: 5.1995. Min Range: -5.1995

Max Act: 4.6980. Min Act: -0.1700

Data Index: 4955468 (Open Web Text)

Max Activating Token Index: 509

Text #16

Max Range: 5.1995. Min Range: -5.1995

Max Act: 4.7127. Min Act: -0.1700

Data Index: 4677578 (Open Web Text)

Max Activating Token Index: 707

Text #17

Max Range: 5.1995. Min Range: -5.1995

Max Act: 4.7386. Min Act: -0.1700

Data Index: 6622034 (Open Web Text)

Max Activating Token Index: 348

Text #18

Max Range: 5.1995. Min Range: -5.1995

Max Act: 4.7186. Min Act: -0.1700

Data Index: 4281155 (Open Web Text)

Max Activating Token Index: 95

Text #19

Max Range: 5.1995. Min Range: -5.1995

Max Act: 4.7161. Min Act: -0.1700

Data Index: 2928593 (Open Web Text)

Max Activating Token Index: 757