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

Dataset: Open Web Text

Neuron 1048 in Layer 6

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: 4.8147. Min Range: -4.8147

Max Act: 4.8147. Min Act: -0.1700

Data Index: 6772032 (Open Web Text)

Max Activating Token Index: 958

Text #1

Max Range: 4.8147. Min Range: -4.8147

Max Act: 4.7575. Min Act: -0.1700

Data Index: 2936037 (Open Web Text)

Max Activating Token Index: 653

Text #2

Max Range: 4.8147. Min Range: -4.8147

Max Act: 4.6965. Min Act: -0.1700

Data Index: 8575251 (Open Web Text)

Max Activating Token Index: 374

Text #3

Max Range: 4.8147. Min Range: -4.8147

Max Act: 4.6447. Min Act: -0.1700

Data Index: 5256973 (Open Web Text)

Max Activating Token Index: 533

Text #4

Max Range: 4.8147. Min Range: -4.8147

Max Act: 4.6536. Min Act: -0.1700

Data Index: 2097194 (Open Web Text)

Max Activating Token Index: 664

Text #5

Max Range: 4.8147. Min Range: -4.8147

Max Act: 4.6246. Min Act: -0.1700

Data Index: 1734076 (Open Web Text)

Max Activating Token Index: 614

Text #6

Max Range: 4.8147. Min Range: -4.8147

Max Act: 4.6282. Min Act: -0.1700

Data Index: 4027401 (Open Web Text)

Max Activating Token Index: 889

Text #7

Max Range: 4.8147. Min Range: -4.8147

Max Act: 4.6465. Min Act: -0.1700

Data Index: 1845897 (Open Web Text)

Max Activating Token Index: 77

Text #8

Max Range: 4.8147. Min Range: -4.8147

Max Act: 4.6480. Min Act: -0.1700

Data Index: 6356243 (Open Web Text)

Max Activating Token Index: 809

Text #9

Max Range: 4.8147. Min Range: -4.8147

Max Act: 4.6033. Min Act: -0.1700

Data Index: 3028112 (Open Web Text)

Max Activating Token Index: 607

Text #10

Max Range: 4.8147. Min Range: -4.8147

Max Act: 4.6170. Min Act: -0.1700

Data Index: 7067973 (Open Web Text)

Max Activating Token Index: 554

Text #11

Max Range: 4.8147. Min Range: -4.8147

Max Act: 4.5872. Min Act: -0.1700

Data Index: 6485772 (Open Web Text)

Max Activating Token Index: 49

Text #12

Max Range: 4.8147. Min Range: -4.8147

Max Act: 4.5915. Min Act: -0.1700

Data Index: 970192 (Open Web Text)

Max Activating Token Index: 869

Text #13

Max Range: 4.8147. Min Range: -4.8147

Max Act: 4.5670. Min Act: -0.1700

Data Index: 6132501 (Open Web Text)

Max Activating Token Index: 443

Text #14

Max Range: 4.8147. Min Range: -4.8147

Max Act: 4.5813. Min Act: -0.1700

Data Index: 5941753 (Open Web Text)

Max Activating Token Index: 956

Text #15

Max Range: 4.8147. Min Range: -4.8147

Max Act: 4.5792. Min Act: -0.1700

Data Index: 3898084 (Open Web Text)

Max Activating Token Index: 266

Text #16

Max Range: 4.8147. Min Range: -4.8147

Max Act: 4.5991. Min Act: -0.1700

Data Index: 5726753 (Open Web Text)

Max Activating Token Index: 178

Text #17

Max Range: 4.8147. Min Range: -4.8147

Max Act: 4.5686. Min Act: -0.1700

Data Index: 5504187 (Open Web Text)

Max Activating Token Index: 339

Text #18

Max Range: 4.8147. Min Range: -4.8147

Max Act: 4.5718. Min Act: -0.1700

Data Index: 7262105 (Open Web Text)

Max Activating Token Index: 252

Text #19

Max Range: 4.8147. Min Range: -4.8147

Max Act: 4.5788. Min Act: -0.1700

Data Index: 8247090 (Open Web Text)

Max Activating Token Index: 677