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

Dataset: Open Web Text

Neuron 2032 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: 5.8607. Min Range: -5.8607

Max Act: 5.8607. Min Act: -0.1700

Data Index: 3559175 (Open Web Text)

Max Activating Token Index: 542

Text #1

Max Range: 5.8607. Min Range: -5.8607

Max Act: 5.7192. Min Act: -0.1700

Data Index: 3859542 (Open Web Text)

Max Activating Token Index: 515

Text #2

Max Range: 5.8607. Min Range: -5.8607

Max Act: 5.8022. Min Act: -0.1700

Data Index: 5295302 (Open Web Text)

Max Activating Token Index: 330

Text #3

Max Range: 5.8607. Min Range: -5.8607

Max Act: 5.7377. Min Act: -0.1700

Data Index: 7903725 (Open Web Text)

Max Activating Token Index: 734

Text #4

Max Range: 5.8607. Min Range: -5.8607

Max Act: 5.7169. Min Act: -0.1700

Data Index: 4061624 (Open Web Text)

Max Activating Token Index: 207

Text #5

Max Range: 5.8607. Min Range: -5.8607

Max Act: 5.6590. Min Act: -0.1700

Data Index: 3372344 (Open Web Text)

Max Activating Token Index: 484

Text #6

Max Range: 5.8607. Min Range: -5.8607

Max Act: 5.6929. Min Act: -0.1700

Data Index: 8279698 (Open Web Text)

Max Activating Token Index: 693

Text #7

Max Range: 5.8607. Min Range: -5.8607

Max Act: 5.6901. Min Act: -0.1700

Data Index: 3621050 (Open Web Text)

Max Activating Token Index: 672

Text #8

Max Range: 5.8607. Min Range: -5.8607

Max Act: 5.6798. Min Act: -0.1700

Data Index: 7803312 (Open Web Text)

Max Activating Token Index: 250

Text #9

Max Range: 5.8607. Min Range: -5.8607

Max Act: 5.6691. Min Act: -0.1700

Data Index: 5490259 (Open Web Text)

Max Activating Token Index: 357

Text #10

Max Range: 5.8607. Min Range: -5.8607

Max Act: 5.6626. Min Act: -0.1700

Data Index: 1334447 (Open Web Text)

Max Activating Token Index: 135

Text #11

Max Range: 5.8607. Min Range: -5.8607

Max Act: 5.6137. Min Act: -0.1700

Data Index: 2674339 (Open Web Text)

Max Activating Token Index: 447

Text #12

Max Range: 5.8607. Min Range: -5.8607

Max Act: 5.6354. Min Act: -0.1700

Data Index: 8548069 (Open Web Text)

Max Activating Token Index: 177

Text #13

Max Range: 5.8607. Min Range: -5.8607

Max Act: 5.5663. Min Act: -0.1700

Data Index: 7359596 (Open Web Text)

Max Activating Token Index: 323

Text #14

Max Range: 5.8607. Min Range: -5.8607

Max Act: 5.5803. Min Act: -0.1700

Data Index: 8414726 (Open Web Text)

Max Activating Token Index: 256

Text #15

Max Range: 5.8607. Min Range: -5.8607

Max Act: 5.6243. Min Act: -0.1700

Data Index: 2901858 (Open Web Text)

Max Activating Token Index: 524

Text #16

Max Range: 5.8607. Min Range: -5.8607

Max Act: 5.5456. Min Act: -0.1700

Data Index: 1406943 (Open Web Text)

Max Activating Token Index: 325

Text #17

Max Range: 5.8607. Min Range: -5.8607

Max Act: 5.5544. Min Act: -0.1700

Data Index: 5404543 (Open Web Text)

Max Activating Token Index: 367

Text #18

Max Range: 5.8607. Min Range: -5.8607

Max Act: 5.5079. Min Act: -0.1700

Data Index: 2930824 (Open Web Text)

Max Activating Token Index: 208

Text #19

Max Range: 5.8607. Min Range: -5.8607

Max Act: 5.5229. Min Act: -0.1700

Data Index: 1938641 (Open Web Text)

Max Activating Token Index: 306