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

Dataset: Open Web Text

Neuron 676 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: 4.5348. Min Range: -4.5348

Max Act: 4.5348. Min Act: -0.1700

Data Index: 4019765 (Open Web Text)

Max Activating Token Index: 891

Text #1

Max Range: 4.5348. Min Range: -4.5348

Max Act: 4.3964. Min Act: -0.1700

Data Index: 4645635 (Open Web Text)

Max Activating Token Index: 226

Text #2

Max Range: 4.5348. Min Range: -4.5348

Max Act: 4.2791. Min Act: -0.1700

Data Index: 2873592 (Open Web Text)

Max Activating Token Index: 761

Text #3

Max Range: 4.5348. Min Range: -4.5348

Max Act: 4.1433. Min Act: -0.1700

Data Index: 8187536 (Open Web Text)

Max Activating Token Index: 534

Text #4

Max Range: 4.5348. Min Range: -4.5348

Max Act: 4.1086. Min Act: -0.1700

Data Index: 7244135 (Open Web Text)

Max Activating Token Index: 130

Text #5

Max Range: 4.5348. Min Range: -4.5348

Max Act: 4.1132. Min Act: -0.1700

Data Index: 5110910 (Open Web Text)

Max Activating Token Index: 529

Text #6

Max Range: 4.5348. Min Range: -4.5348

Max Act: 4.0576. Min Act: -0.1700

Data Index: 8720501 (Open Web Text)

Max Activating Token Index: 827

Text #7

Max Range: 4.5348. Min Range: -4.5348

Max Act: 4.0313. Min Act: -0.1700

Data Index: 5684368 (Open Web Text)

Max Activating Token Index: 265

Text #8

Max Range: 4.5348. Min Range: -4.5348

Max Act: 4.0768. Min Act: -0.1700

Data Index: 4912169 (Open Web Text)

Max Activating Token Index: 500

Text #9

Max Range: 4.5348. Min Range: -4.5348

Max Act: 4.1267. Min Act: -0.1700

Data Index: 7914065 (Open Web Text)

Max Activating Token Index: 571

Text #10

Max Range: 4.5348. Min Range: -4.5348

Max Act: 4.1373. Min Act: -0.1700

Data Index: 4414492 (Open Web Text)

Max Activating Token Index: 995

Text #11

Max Range: 4.5348. Min Range: -4.5348

Max Act: 4.0348. Min Act: -0.1700

Data Index: 3174345 (Open Web Text)

Max Activating Token Index: 579

Text #12

Max Range: 4.5348. Min Range: -4.5348

Max Act: 4.0702. Min Act: -0.1700

Data Index: 5212300 (Open Web Text)

Max Activating Token Index: 555

Text #13

Max Range: 4.5348. Min Range: -4.5348

Max Act: 4.0370. Min Act: -0.1700

Data Index: 5620648 (Open Web Text)

Max Activating Token Index: 287

Text #14

Max Range: 4.5348. Min Range: -4.5348

Max Act: 4.0677. Min Act: -0.1700

Data Index: 4650261 (Open Web Text)

Max Activating Token Index: 742

Text #15

Max Range: 4.5348. Min Range: -4.5348

Max Act: 3.9635. Min Act: -0.1700

Data Index: 3147752 (Open Web Text)

Max Activating Token Index: 480

Text #16

Max Range: 4.5348. Min Range: -4.5348

Max Act: 4.0488. Min Act: -0.1700

Data Index: 4834454 (Open Web Text)

Max Activating Token Index: 652

Text #17

Max Range: 4.5348. Min Range: -4.5348

Max Act: 4.0156. Min Act: -0.1700

Data Index: 4498931 (Open Web Text)

Max Activating Token Index: 792

Text #18

Max Range: 4.5348. Min Range: -4.5348

Max Act: 4.0338. Min Act: -0.1700

Data Index: 6325840 (Open Web Text)

Max Activating Token Index: 196

Text #19

Max Range: 4.5348. Min Range: -4.5348

Max Act: 3.9413. Min Act: -0.1700

Data Index: 891382 (Open Web Text)

Max Activating Token Index: 581