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

Dataset: Open Web Text

Neuron 1354 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: 5.1021. Min Range: -5.1021

Max Act: 5.1021. Min Act: -0.1700

Data Index: 4288438 (Open Web Text)

Max Activating Token Index: 829

Text #1

Max Range: 5.1021. Min Range: -5.1021

Max Act: 5.0182. Min Act: -0.1700

Data Index: 6885730 (Open Web Text)

Max Activating Token Index: 727

Text #2

Max Range: 5.1021. Min Range: -5.1021

Max Act: 4.9926. Min Act: -0.1700

Data Index: 6422010 (Open Web Text)

Max Activating Token Index: 492

Text #3

Max Range: 5.1021. Min Range: -5.1021

Max Act: 5.0272. Min Act: -0.1700

Data Index: 6151447 (Open Web Text)

Max Activating Token Index: 874

Text #4

Max Range: 5.1021. Min Range: -5.1021

Max Act: 5.0009. Min Act: -0.1700

Data Index: 4557167 (Open Web Text)

Max Activating Token Index: 108

Text #5

Max Range: 5.1021. Min Range: -5.1021

Max Act: 5.0056. Min Act: -0.1700

Data Index: 2232333 (Open Web Text)

Max Activating Token Index: 924

Text #6

Max Range: 5.1021. Min Range: -5.1021

Max Act: 4.9368. Min Act: -0.1700

Data Index: 8209108 (Open Web Text)

Max Activating Token Index: 729

Text #7

Max Range: 5.1021. Min Range: -5.1021

Max Act: 4.9104. Min Act: -0.1700

Data Index: 2273602 (Open Web Text)

Max Activating Token Index: 500

Text #8

Max Range: 5.1021. Min Range: -5.1021

Max Act: 4.9849. Min Act: -0.1700

Data Index: 5833407 (Open Web Text)

Max Activating Token Index: 575

Text #9

Max Range: 5.1021. Min Range: -5.1021

Max Act: 4.9188. Min Act: -0.1700

Data Index: 1780274 (Open Web Text)

Max Activating Token Index: 213

Text #10

Max Range: 5.1021. Min Range: -5.1021

Max Act: 4.9418. Min Act: -0.1700

Data Index: 414550 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 5.1021. Min Range: -5.1021

Max Act: 4.9111. Min Act: -0.1700

Data Index: 8477368 (Open Web Text)

Max Activating Token Index: 422

Text #12

Max Range: 5.1021. Min Range: -5.1021

Max Act: 4.9347. Min Act: -0.1700

Data Index: 6178569 (Open Web Text)

Max Activating Token Index: 503

Text #13

Max Range: 5.1021. Min Range: -5.1021

Max Act: 4.8368. Min Act: -0.1700

Data Index: 5066752 (Open Web Text)

Max Activating Token Index: 886

Text #14

Max Range: 5.1021. Min Range: -5.1021

Max Act: 4.9199. Min Act: -0.1700

Data Index: 266566 (Open Web Text)

Max Activating Token Index: 1019

Text #15

Max Range: 5.1021. Min Range: -5.1021

Max Act: 4.9204. Min Act: -0.1700

Data Index: 3170373 (Open Web Text)

Max Activating Token Index: 171

Text #16

Max Range: 5.1021. Min Range: -5.1021

Max Act: 4.9399. Min Act: -0.1700

Data Index: 4217624 (Open Web Text)

Max Activating Token Index: 480

Text #17

Max Range: 5.1021. Min Range: -5.1021

Max Act: 4.9242. Min Act: -0.1700

Data Index: 7918980 (Open Web Text)

Max Activating Token Index: 39

Text #18

Max Range: 5.1021. Min Range: -5.1021

Max Act: 4.9287. Min Act: -0.1700

Data Index: 7654577 (Open Web Text)

Max Activating Token Index: 611

Text #19

Max Range: 5.1021. Min Range: -5.1021

Max Act: 4.9087. Min Act: -0.1700

Data Index: 3929420 (Open Web Text)

Max Activating Token Index: 29