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

Dataset: Open Web Text

Neuron 95 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: 3.5640. Min Range: -3.5640

Max Act: 3.5585. Min Act: -0.1700

Data Index: 7167325 (Open Web Text)

Max Activating Token Index: 1009

Text #1

Max Range: 3.5640. Min Range: -3.5640

Max Act: 3.5640. Min Act: -0.1700

Data Index: 7158807 (Open Web Text)

Max Activating Token Index: 696

Text #2

Max Range: 3.5640. Min Range: -3.5640

Max Act: 3.5536. Min Act: -0.1700

Data Index: 8734386 (Open Web Text)

Max Activating Token Index: 188

Text #3

Max Range: 3.5640. Min Range: -3.5640

Max Act: 3.5421. Min Act: -0.1700

Data Index: 4347892 (Open Web Text)

Max Activating Token Index: 522

Text #4

Max Range: 3.5640. Min Range: -3.5640

Max Act: 3.5566. Min Act: -0.1700

Data Index: 3899428 (Open Web Text)

Max Activating Token Index: 1016

Text #5

Max Range: 3.5640. Min Range: -3.5640

Max Act: 3.5398. Min Act: -0.1700

Data Index: 1157014 (Open Web Text)

Max Activating Token Index: 167

Text #6

Max Range: 3.5640. Min Range: -3.5640

Max Act: 3.5139. Min Act: -0.1700

Data Index: 4540063 (Open Web Text)

Max Activating Token Index: 341

Text #7

Max Range: 3.5640. Min Range: -3.5640

Max Act: 3.4797. Min Act: -0.1700

Data Index: 5327851 (Open Web Text)

Max Activating Token Index: 948

Text #8

Max Range: 3.5640. Min Range: -3.5640

Max Act: 3.4175. Min Act: -0.1700

Data Index: 8194328 (Open Web Text)

Max Activating Token Index: 897

Text #9

Max Range: 3.5640. Min Range: -3.5640

Max Act: 3.4473. Min Act: -0.1700

Data Index: 3567569 (Open Web Text)

Max Activating Token Index: 864

Text #10

Max Range: 3.5640. Min Range: -3.5640

Max Act: 3.4382. Min Act: -0.1700

Data Index: 7878086 (Open Web Text)

Max Activating Token Index: 399

Text #11

Max Range: 3.5640. Min Range: -3.5640

Max Act: 3.4098. Min Act: -0.1700

Data Index: 3037780 (Open Web Text)

Max Activating Token Index: 905

Text #12

Max Range: 3.5640. Min Range: -3.5640

Max Act: 3.4077. Min Act: -0.1700

Data Index: 305300 (Open Web Text)

Max Activating Token Index: 496

Text #13

Max Range: 3.5640. Min Range: -3.5640

Max Act: 3.4066. Min Act: -0.1700

Data Index: 4258287 (Open Web Text)

Max Activating Token Index: 822

Text #14

Max Range: 3.5640. Min Range: -3.5640

Max Act: 3.3879. Min Act: -0.1700

Data Index: 27147 (Open Web Text)

Max Activating Token Index: 996

Text #15

Max Range: 3.5640. Min Range: -3.5640

Max Act: 3.4000. Min Act: -0.1700

Data Index: 2135595 (Open Web Text)

Max Activating Token Index: 640

Text #16

Max Range: 3.5640. Min Range: -3.5640

Max Act: 3.3944. Min Act: -0.1700

Data Index: 743918 (Open Web Text)

Max Activating Token Index: 600

Text #17

Max Range: 3.5640. Min Range: -3.5640

Max Act: 3.3880. Min Act: -0.1700

Data Index: 5849952 (Open Web Text)

Max Activating Token Index: 227

Text #18

Max Range: 3.5640. Min Range: -3.5640

Max Act: 3.3893. Min Act: -0.1700

Data Index: 6355052 (Open Web Text)

Max Activating Token Index: 175

Text #19

Max Range: 3.5640. Min Range: -3.5640

Max Act: 3.3842. Min Act: -0.1700

Data Index: 3972734 (Open Web Text)

Max Activating Token Index: 140