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

Dataset: Open Web Text

Neuron 1829 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: 1.5462. Min Range: -1.5462

Max Act: 1.5462. Min Act: -0.0258

Data Index: 5626479 (Open Web Text)

Max Activating Token Index: 1012

Text #1

Max Range: 1.5462. Min Range: -1.5462

Max Act: 1.5330. Min Act: -0.1107

Data Index: 3731535 (Open Web Text)

Max Activating Token Index: 1016

Text #2

Max Range: 1.5462. Min Range: -1.5462

Max Act: 1.5380. Min Act: -0.0799

Data Index: 3709620 (Open Web Text)

Max Activating Token Index: 1021

Text #3

Max Range: 1.5462. Min Range: -1.5462

Max Act: 1.5262. Min Act: -0.0701

Data Index: 8408191 (Open Web Text)

Max Activating Token Index: 514

Text #4

Max Range: 1.5462. Min Range: -1.5462

Max Act: 1.5304. Min Act: -0.0252

Data Index: 8826145 (Open Web Text)

Max Activating Token Index: 1014

Text #5

Max Range: 1.5462. Min Range: -1.5462

Max Act: 1.5015. Min Act: -0.0720

Data Index: 6652196 (Open Web Text)

Max Activating Token Index: 709

Text #6

Max Range: 1.5462. Min Range: -1.5462

Max Act: 1.5096. Min Act: -0.0662

Data Index: 5578656 (Open Web Text)

Max Activating Token Index: 1021

Text #7

Max Range: 1.5462. Min Range: -1.5462

Max Act: 1.5071. Min Act: -0.0849

Data Index: 8700678 (Open Web Text)

Max Activating Token Index: 526

Text #8

Max Range: 1.5462. Min Range: -1.5462

Max Act: 1.5104. Min Act: -0.0129

Data Index: 816647 (Open Web Text)

Max Activating Token Index: 464

Text #9

Max Range: 1.5462. Min Range: -1.5462

Max Act: 1.5084. Min Act: -0.1447

Data Index: 702869 (Open Web Text)

Max Activating Token Index: 1007

Text #10

Max Range: 1.5462. Min Range: -1.5462

Max Act: 1.4860. Min Act: -0.1172

Data Index: 1934615 (Open Web Text)

Max Activating Token Index: 996

Text #11

Max Range: 1.5462. Min Range: -1.5462

Max Act: 1.5192. Min Act: -0.0653

Data Index: 1001198 (Open Web Text)

Max Activating Token Index: 1022

Text #12

Max Range: 1.5462. Min Range: -1.5462

Max Act: 1.5146. Min Act: -0.0317

Data Index: 8688741 (Open Web Text)

Max Activating Token Index: 696

Text #13

Max Range: 1.5462. Min Range: -1.5462

Max Act: 1.5100. Min Act: -0.0207

Data Index: 8113732 (Open Web Text)

Max Activating Token Index: 1022

Text #14

Max Range: 1.5462. Min Range: -1.5462

Max Act: 1.4810. Min Act: -0.0455

Data Index: 384516 (Open Web Text)

Max Activating Token Index: 1007

Text #15

Max Range: 1.5462. Min Range: -1.5462

Max Act: 1.4866. Min Act: -0.1163

Data Index: 6467448 (Open Web Text)

Max Activating Token Index: 999

Text #16

Max Range: 1.5462. Min Range: -1.5462

Max Act: 1.4917. Min Act: -0.0769

Data Index: 1586404 (Open Web Text)

Max Activating Token Index: 685

Text #17

Max Range: 1.5462. Min Range: -1.5462

Max Act: 1.4988. Min Act: -0.1321

Data Index: 6521638 (Open Web Text)

Max Activating Token Index: 1020

Text #18

Max Range: 1.5462. Min Range: -1.5462

Max Act: 1.4891. Min Act: -0.0909

Data Index: 1306297 (Open Web Text)

Max Activating Token Index: 593

Text #19

Max Range: 1.5462. Min Range: -1.5462

Max Act: 1.5030. Min Act: -0.0556

Data Index: 6676198 (Open Web Text)

Max Activating Token Index: 1013