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

Dataset: Open Web Text

Neuron 1481 in Layer 3

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: 4.0814. Min Range: -4.0814

Max Act: 4.0601. Min Act: -0.1700

Data Index: 3561810 (Open Web Text)

Max Activating Token Index: 591

Text #1

Max Range: 4.0814. Min Range: -4.0814

Max Act: 4.0814. Min Act: -0.1700

Data Index: 5566947 (Open Web Text)

Max Activating Token Index: 661

Text #2

Max Range: 4.0814. Min Range: -4.0814

Max Act: 4.0111. Min Act: -0.1700

Data Index: 3561811 (Open Web Text)

Max Activating Token Index: 467

Text #3

Max Range: 4.0814. Min Range: -4.0814

Max Act: 3.9381. Min Act: -0.1700

Data Index: 3561809 (Open Web Text)

Max Activating Token Index: 974

Text #4

Max Range: 4.0814. Min Range: -4.0814

Max Act: 3.9094. Min Act: -0.1700

Data Index: 4572281 (Open Web Text)

Max Activating Token Index: 403

Text #5

Max Range: 4.0814. Min Range: -4.0814

Max Act: 3.8389. Min Act: -0.1700

Data Index: 7628247 (Open Web Text)

Max Activating Token Index: 776

Text #6

Max Range: 4.0814. Min Range: -4.0814

Max Act: 3.8327. Min Act: -0.1700

Data Index: 7241107 (Open Web Text)

Max Activating Token Index: 768

Text #7

Max Range: 4.0814. Min Range: -4.0814

Max Act: 3.8025. Min Act: -0.1700

Data Index: 629257 (Open Web Text)

Max Activating Token Index: 833

Text #8

Max Range: 4.0814. Min Range: -4.0814

Max Act: 3.7775. Min Act: -0.1700

Data Index: 629258 (Open Web Text)

Max Activating Token Index: 483

Text #9

Max Range: 4.0814. Min Range: -4.0814

Max Act: 3.7713. Min Act: -0.1700

Data Index: 7627212 (Open Web Text)

Max Activating Token Index: 1013

Text #10

Max Range: 4.0814. Min Range: -4.0814

Max Act: 3.7070. Min Act: -0.1700

Data Index: 191043 (Open Web Text)

Max Activating Token Index: 863

Text #11

Max Range: 4.0814. Min Range: -4.0814

Max Act: 3.6899. Min Act: -0.1700

Data Index: 6785524 (Open Web Text)

Max Activating Token Index: 393

Text #12

Max Range: 4.0814. Min Range: -4.0814

Max Act: 3.6916. Min Act: -0.1700

Data Index: 7785231 (Open Web Text)

Max Activating Token Index: 221

Text #13

Max Range: 4.0814. Min Range: -4.0814

Max Act: 3.6905. Min Act: -0.1700

Data Index: 1422688 (Open Web Text)

Max Activating Token Index: 673

Text #14

Max Range: 4.0814. Min Range: -4.0814

Max Act: 3.6338. Min Act: -0.1700

Data Index: 758898 (Open Web Text)

Max Activating Token Index: 105

Text #15

Max Range: 4.0814. Min Range: -4.0814

Max Act: 3.6285. Min Act: -0.1700

Data Index: 6531172 (Open Web Text)

Max Activating Token Index: 370

Text #16

Max Range: 4.0814. Min Range: -4.0814

Max Act: 3.6487. Min Act: -0.1700

Data Index: 8796674 (Open Web Text)

Max Activating Token Index: 381

Text #17

Max Range: 4.0814. Min Range: -4.0814

Max Act: 3.5900. Min Act: -0.1700

Data Index: 1880136 (Open Web Text)

Max Activating Token Index: 976

Text #18

Max Range: 4.0814. Min Range: -4.0814

Max Act: 3.5690. Min Act: -0.1700

Data Index: 1268277 (Open Web Text)

Max Activating Token Index: 904

Text #19

Max Range: 4.0814. Min Range: -4.0814

Max Act: 3.5710. Min Act: -0.1700

Data Index: 2245443 (Open Web Text)

Max Activating Token Index: 243