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

Dataset: Open Web Text

Neuron 2858 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: 1.5514. Min Range: -1.5514

Max Act: 1.5514. Min Act: -0.0372

Data Index: 5804691 (Open Web Text)

Max Activating Token Index: 1021

Text #1

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.5356. Min Act: -0.0372

Data Index: 3028695 (Open Web Text)

Max Activating Token Index: 1021

Text #2

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.5414. Min Act: -0.0421

Data Index: 2763789 (Open Web Text)

Max Activating Token Index: 1021

Text #3

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.5366. Min Act: 0.0678

Data Index: 4020780 (Open Web Text)

Max Activating Token Index: 1007

Text #4

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.5200. Min Act: 0.0083

Data Index: 6520193 (Open Web Text)

Max Activating Token Index: 1018

Text #5

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.5270. Min Act: 0.0088

Data Index: 6397444 (Open Web Text)

Max Activating Token Index: 1019

Text #6

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.5088. Min Act: -0.0237

Data Index: 6497134 (Open Web Text)

Max Activating Token Index: 1022

Text #7

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.5131. Min Act: 0.0187

Data Index: 1251598 (Open Web Text)

Max Activating Token Index: 1012

Text #8

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.5035. Min Act: -0.0489

Data Index: 2179177 (Open Web Text)

Max Activating Token Index: 1021

Text #9

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.5075. Min Act: -0.0093

Data Index: 3437034 (Open Web Text)

Max Activating Token Index: 1022

Text #10

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.5047. Min Act: 0.0058

Data Index: 3989399 (Open Web Text)

Max Activating Token Index: 1020

Text #11

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.5000. Min Act: -0.0617

Data Index: 7278151 (Open Web Text)

Max Activating Token Index: 1022

Text #12

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.4783. Min Act: -0.0126

Data Index: 2005982 (Open Web Text)

Max Activating Token Index: 1018

Text #13

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.4919. Min Act: -0.0156

Data Index: 3128659 (Open Web Text)

Max Activating Token Index: 1012

Text #14

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.4869. Min Act: -0.0157

Data Index: 453135 (Open Web Text)

Max Activating Token Index: 1014

Text #15

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.4862. Min Act: 0.0042

Data Index: 7950307 (Open Web Text)

Max Activating Token Index: 1022

Text #16

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.4879. Min Act: -0.0252

Data Index: 1471574 (Open Web Text)

Max Activating Token Index: 1020

Text #17

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.4902. Min Act: -0.0495

Data Index: 5634823 (Open Web Text)

Max Activating Token Index: 1021

Text #18

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.4734. Min Act: -0.0073

Data Index: 4183298 (Open Web Text)

Max Activating Token Index: 1021

Text #19

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.4792. Min Act: -0.0727

Data Index: 2743290 (Open Web Text)

Max Activating Token Index: 1021