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

Dataset: Open Web Text

Neuron 2618 in Layer 1

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: 3.0813. Min Range: -3.0813

Max Act: 3.0813. Min Act: -0.1700

Data Index: 1092480 (Open Web Text)

Max Activating Token Index: 199

Text #1

Max Range: 3.0813. Min Range: -3.0813

Max Act: 3.0605. Min Act: -0.1700

Data Index: 8724578 (Open Web Text)

Max Activating Token Index: 49

Text #2

Max Range: 3.0813. Min Range: -3.0813

Max Act: 3.0233. Min Act: -0.1700

Data Index: 5288354 (Open Web Text)

Max Activating Token Index: 940

Text #3

Max Range: 3.0813. Min Range: -3.0813

Max Act: 3.0040. Min Act: -0.1700

Data Index: 3504196 (Open Web Text)

Max Activating Token Index: 299

Text #4

Max Range: 3.0813. Min Range: -3.0813

Max Act: 3.0170. Min Act: -0.1700

Data Index: 1528955 (Open Web Text)

Max Activating Token Index: 202

Text #5

Max Range: 3.0813. Min Range: -3.0813

Max Act: 3.0130. Min Act: -0.1700

Data Index: 2481580 (Open Web Text)

Max Activating Token Index: 45

Text #6

Max Range: 3.0813. Min Range: -3.0813

Max Act: 3.0255. Min Act: -0.1700

Data Index: 650764 (Open Web Text)

Max Activating Token Index: 432

Text #7

Max Range: 3.0813. Min Range: -3.0813

Max Act: 3.0021. Min Act: -0.1700

Data Index: 5041763 (Open Web Text)

Max Activating Token Index: 441

Text #8

Max Range: 3.0813. Min Range: -3.0813

Max Act: 2.9877. Min Act: -0.1700

Data Index: 5288346 (Open Web Text)

Max Activating Token Index: 189

Text #9

Max Range: 3.0813. Min Range: -3.0813

Max Act: 2.9941. Min Act: -0.1700

Data Index: 2058664 (Open Web Text)

Max Activating Token Index: 191

Text #10

Max Range: 3.0813. Min Range: -3.0813

Max Act: 3.0001. Min Act: -0.1700

Data Index: 5692401 (Open Web Text)

Max Activating Token Index: 657

Text #11

Max Range: 3.0813. Min Range: -3.0813

Max Act: 2.9884. Min Act: -0.1700

Data Index: 5645186 (Open Web Text)

Max Activating Token Index: 19

Text #12

Max Range: 3.0813. Min Range: -3.0813

Max Act: 2.9928. Min Act: -0.1700

Data Index: 5346757 (Open Web Text)

Max Activating Token Index: 360

Text #13

Max Range: 3.0813. Min Range: -3.0813

Max Act: 2.9873. Min Act: -0.1700

Data Index: 5318649 (Open Web Text)

Max Activating Token Index: 713

Text #14

Max Range: 3.0813. Min Range: -3.0813

Max Act: 2.9763. Min Act: -0.1700

Data Index: 1320130 (Open Web Text)

Max Activating Token Index: 792

Text #15

Max Range: 3.0813. Min Range: -3.0813

Max Act: 2.9837. Min Act: -0.1700

Data Index: 375674 (Open Web Text)

Max Activating Token Index: 240

Text #16

Max Range: 3.0813. Min Range: -3.0813

Max Act: 2.9535. Min Act: -0.1700

Data Index: 718970 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 3.0813. Min Range: -3.0813

Max Act: 2.9552. Min Act: -0.1700

Data Index: 1680504 (Open Web Text)

Max Activating Token Index: 562

Text #18

Max Range: 3.0813. Min Range: -3.0813

Max Act: 2.9493. Min Act: -0.1700

Data Index: 7220817 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 3.0813. Min Range: -3.0813

Max Act: 2.9252. Min Act: -0.1700

Data Index: 3743029 (Open Web Text)

Max Activating Token Index: 425