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

Dataset: Open Web Text

Neuron 749 in Layer 0

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: 4.8989. Min Range: -4.8989

Max Act: 4.8989. Min Act: -0.1700

Data Index: 7762695 (Open Web Text)

Max Activating Token Index: 49

Text #1

Max Range: 4.8989. Min Range: -4.8989

Max Act: 4.6752. Min Act: -0.1700

Data Index: 6096926 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 4.8989. Min Range: -4.8989

Max Act: 4.6418. Min Act: -0.1700

Data Index: 4279046 (Open Web Text)

Max Activating Token Index: 269

Text #3

Max Range: 4.8989. Min Range: -4.8989

Max Act: 4.6462. Min Act: -0.1700

Data Index: 1271360 (Open Web Text)

Max Activating Token Index: 509

Text #4

Max Range: 4.8989. Min Range: -4.8989

Max Act: 4.6207. Min Act: -0.1700

Data Index: 4149549 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 4.8989. Min Range: -4.8989

Max Act: 4.5739. Min Act: -0.1700

Data Index: 2320630 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 4.8989. Min Range: -4.8989

Max Act: 4.5457. Min Act: -0.1700

Data Index: 3476258 (Open Web Text)

Max Activating Token Index: 14

Text #7

Max Range: 4.8989. Min Range: -4.8989

Max Act: 4.5428. Min Act: -0.1700

Data Index: 1320086 (Open Web Text)

Max Activating Token Index: 886

Text #8

Max Range: 4.8989. Min Range: -4.8989

Max Act: 4.5041. Min Act: -0.1700

Data Index: 3054926 (Open Web Text)

Max Activating Token Index: 827

Text #9

Max Range: 4.8989. Min Range: -4.8989

Max Act: 4.5173. Min Act: -0.1700

Data Index: 3128054 (Open Web Text)

Max Activating Token Index: 398

Text #10

Max Range: 4.8989. Min Range: -4.8989

Max Act: 4.5233. Min Act: -0.1700

Data Index: 1122504 (Open Web Text)

Max Activating Token Index: 50

Text #11

Max Range: 4.8989. Min Range: -4.8989

Max Act: 4.5199. Min Act: -0.1700

Data Index: 3043990 (Open Web Text)

Max Activating Token Index: 870

Text #12

Max Range: 4.8989. Min Range: -4.8989

Max Act: 4.5164. Min Act: -0.1700

Data Index: 5091855 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 4.8989. Min Range: -4.8989

Max Act: 4.5284. Min Act: -0.1700

Data Index: 2918938 (Open Web Text)

Max Activating Token Index: 9

Text #14

Max Range: 4.8989. Min Range: -4.8989

Max Act: 4.5321. Min Act: -0.1700

Data Index: 4662943 (Open Web Text)

Max Activating Token Index: 35

Text #15

Max Range: 4.8989. Min Range: -4.8989

Max Act: 4.5127. Min Act: -0.1700

Data Index: 2692898 (Open Web Text)

Max Activating Token Index: 399

Text #16

Max Range: 4.8989. Min Range: -4.8989

Max Act: 4.5166. Min Act: -0.1700

Data Index: 7268072 (Open Web Text)

Max Activating Token Index: 45

Text #17

Max Range: 4.8989. Min Range: -4.8989

Max Act: 4.5228. Min Act: -0.1700

Data Index: 1919894 (Open Web Text)

Max Activating Token Index: 483

Text #18

Max Range: 4.8989. Min Range: -4.8989

Max Act: 4.5238. Min Act: -0.1700

Data Index: 4855775 (Open Web Text)

Max Activating Token Index: 556

Text #19

Max Range: 4.8989. Min Range: -4.8989

Max Act: 4.5380. Min Act: -0.1700

Data Index: 8584866 (Open Web Text)

Max Activating Token Index: 18