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

Dataset: Open Web Text

Neuron 517 in Layer 2

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: 4.8741. Min Range: -4.8741

Max Act: 4.8741. Min Act: -0.1700

Data Index: 459618 (Open Web Text)

Max Activating Token Index: 10

Text #1

Max Range: 4.8741. Min Range: -4.8741

Max Act: 4.8325. Min Act: -0.1700

Data Index: 7263552 (Open Web Text)

Max Activating Token Index: 895

Text #2

Max Range: 4.8741. Min Range: -4.8741

Max Act: 4.7725. Min Act: -0.1700

Data Index: 2665222 (Open Web Text)

Max Activating Token Index: 155

Text #3

Max Range: 4.8741. Min Range: -4.8741

Max Act: 4.7817. Min Act: -0.1700

Data Index: 3530183 (Open Web Text)

Max Activating Token Index: 159

Text #4

Max Range: 4.8741. Min Range: -4.8741

Max Act: 4.7212. Min Act: -0.1700

Data Index: 6597807 (Open Web Text)

Max Activating Token Index: 505

Text #5

Max Range: 4.8741. Min Range: -4.8741

Max Act: 4.6843. Min Act: -0.1700

Data Index: 2557814 (Open Web Text)

Max Activating Token Index: 21

Text #6

Max Range: 4.8741. Min Range: -4.8741

Max Act: 4.6863. Min Act: -0.1700

Data Index: 3319254 (Open Web Text)

Max Activating Token Index: 282

Text #7

Max Range: 4.8741. Min Range: -4.8741

Max Act: 4.6860. Min Act: -0.1700

Data Index: 8160315 (Open Web Text)

Max Activating Token Index: 602

Text #8

Max Range: 4.8741. Min Range: -4.8741

Max Act: 4.6683. Min Act: -0.1700

Data Index: 4237770 (Open Web Text)

Max Activating Token Index: 650

Text #9

Max Range: 4.8741. Min Range: -4.8741

Max Act: 4.6709. Min Act: -0.1700

Data Index: 3466126 (Open Web Text)

Max Activating Token Index: 784

Text #10

Max Range: 4.8741. Min Range: -4.8741

Max Act: 4.6425. Min Act: -0.1700

Data Index: 4120366 (Open Web Text)

Max Activating Token Index: 768

Text #11

Max Range: 4.8741. Min Range: -4.8741

Max Act: 4.6458. Min Act: -0.1700

Data Index: 2159825 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 4.8741. Min Range: -4.8741

Max Act: 4.6275. Min Act: -0.1700

Data Index: 2343565 (Open Web Text)

Max Activating Token Index: 10

Text #13

Max Range: 4.8741. Min Range: -4.8741

Max Act: 4.6181. Min Act: -0.1700

Data Index: 2341128 (Open Web Text)

Max Activating Token Index: 114

Text #14

Max Range: 4.8741. Min Range: -4.8741

Max Act: 4.6162. Min Act: -0.1700

Data Index: 2168961 (Open Web Text)

Max Activating Token Index: 924

Text #15

Max Range: 4.8741. Min Range: -4.8741

Max Act: 4.6127. Min Act: -0.1700

Data Index: 7109483 (Open Web Text)

Max Activating Token Index: 653

Text #16

Max Range: 4.8741. Min Range: -4.8741

Max Act: 4.6224. Min Act: -0.1700

Data Index: 6014170 (Open Web Text)

Max Activating Token Index: 103

Text #17

Max Range: 4.8741. Min Range: -4.8741

Max Act: 4.6207. Min Act: -0.1700

Data Index: 166650 (Open Web Text)

Max Activating Token Index: 936

Text #18

Max Range: 4.8741. Min Range: -4.8741

Max Act: 4.6242. Min Act: -0.1700

Data Index: 4702923 (Open Web Text)

Max Activating Token Index: 670

Text #19

Max Range: 4.8741. Min Range: -4.8741

Max Act: 4.6172. Min Act: -0.1700

Data Index: 2579542 (Open Web Text)

Max Activating Token Index: 281