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

Dataset: Open Web Text

Neuron 1099 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: 5.4292. Min Range: -5.4292

Max Act: 5.4292. Min Act: -0.1700

Data Index: 3418032 (Open Web Text)

Max Activating Token Index: 953

Text #1

Max Range: 5.4292. Min Range: -5.4292

Max Act: 5.2812. Min Act: -0.1700

Data Index: 7877031 (Open Web Text)

Max Activating Token Index: 537

Text #2

Max Range: 5.4292. Min Range: -5.4292

Max Act: 5.2343. Min Act: -0.1700

Data Index: 5477688 (Open Web Text)

Max Activating Token Index: 540

Text #3

Max Range: 5.4292. Min Range: -5.4292

Max Act: 5.1696. Min Act: -0.1700

Data Index: 5616941 (Open Web Text)

Max Activating Token Index: 653

Text #4

Max Range: 5.4292. Min Range: -5.4292

Max Act: 5.1356. Min Act: -0.1700

Data Index: 8110745 (Open Web Text)

Max Activating Token Index: 281

Text #5

Max Range: 5.4292. Min Range: -5.4292

Max Act: 5.1366. Min Act: -0.1695

Data Index: 70022 (Open Web Text)

Max Activating Token Index: 574

Text #6

Max Range: 5.4292. Min Range: -5.4292

Max Act: 5.1302. Min Act: -0.1700

Data Index: 3182467 (Open Web Text)

Max Activating Token Index: 672

Text #7

Max Range: 5.4292. Min Range: -5.4292

Max Act: 5.0802. Min Act: -0.1700

Data Index: 2196147 (Open Web Text)

Max Activating Token Index: 696

Text #8

Max Range: 5.4292. Min Range: -5.4292

Max Act: 5.0739. Min Act: -0.1700

Data Index: 3547495 (Open Web Text)

Max Activating Token Index: 477

Text #9

Max Range: 5.4292. Min Range: -5.4292

Max Act: 5.0836. Min Act: -0.1700

Data Index: 7729137 (Open Web Text)

Max Activating Token Index: 589

Text #10

Max Range: 5.4292. Min Range: -5.4292

Max Act: 5.0871. Min Act: -0.1700

Data Index: 1422245 (Open Web Text)

Max Activating Token Index: 718

Text #11

Max Range: 5.4292. Min Range: -5.4292

Max Act: 5.0741. Min Act: -0.1700

Data Index: 4112416 (Open Web Text)

Max Activating Token Index: 157

Text #12

Max Range: 5.4292. Min Range: -5.4292

Max Act: 5.0352. Min Act: -0.1699

Data Index: 5398911 (Open Web Text)

Max Activating Token Index: 907

Text #13

Max Range: 5.4292. Min Range: -5.4292

Max Act: 5.0488. Min Act: -0.1700

Data Index: 1617650 (Open Web Text)

Max Activating Token Index: 641

Text #14

Max Range: 5.4292. Min Range: -5.4292

Max Act: 5.0082. Min Act: -0.1700

Data Index: 8238003 (Open Web Text)

Max Activating Token Index: 472

Text #15

Max Range: 5.4292. Min Range: -5.4292

Max Act: 5.0216. Min Act: -0.1700

Data Index: 4383635 (Open Web Text)

Max Activating Token Index: 748

Text #16

Max Range: 5.4292. Min Range: -5.4292

Max Act: 5.0489. Min Act: -0.1700

Data Index: 5764176 (Open Web Text)

Max Activating Token Index: 783

Text #17

Max Range: 5.4292. Min Range: -5.4292

Max Act: 5.0333. Min Act: -0.1695

Data Index: 782829 (Open Web Text)

Max Activating Token Index: 806

Text #18

Max Range: 5.4292. Min Range: -5.4292

Max Act: 5.0226. Min Act: -0.1700

Data Index: 1333187 (Open Web Text)

Max Activating Token Index: 151

Text #19

Max Range: 5.4292. Min Range: -5.4292

Max Act: 5.0153. Min Act: -0.1700

Data Index: 7851231 (Open Web Text)

Max Activating Token Index: 255