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

Dataset: Open Web Text

Neuron 1107 in Layer 5

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: 3.2916. Min Range: -3.2916

Max Act: 3.2916. Min Act: -0.1700

Data Index: 8401619 (Open Web Text)

Max Activating Token Index: 906

Text #1

Max Range: 3.2916. Min Range: -3.2916

Max Act: 3.1593. Min Act: -0.1700

Data Index: 8717647 (Open Web Text)

Max Activating Token Index: 753

Text #2

Max Range: 3.2916. Min Range: -3.2916

Max Act: 3.1718. Min Act: -0.1700

Data Index: 5996712 (Open Web Text)

Max Activating Token Index: 831

Text #3

Max Range: 3.2916. Min Range: -3.2916

Max Act: 3.1809. Min Act: -0.1700

Data Index: 5996719 (Open Web Text)

Max Activating Token Index: 587

Text #4

Max Range: 3.2916. Min Range: -3.2916

Max Act: 3.1222. Min Act: -0.1700

Data Index: 8143366 (Open Web Text)

Max Activating Token Index: 863

Text #5

Max Range: 3.2916. Min Range: -3.2916

Max Act: 2.9919. Min Act: -0.1700

Data Index: 8717646 (Open Web Text)

Max Activating Token Index: 618

Text #6

Max Range: 3.2916. Min Range: -3.2916

Max Act: 3.0025. Min Act: -0.1700

Data Index: 5996713 (Open Web Text)

Max Activating Token Index: 189

Text #7

Max Range: 3.2916. Min Range: -3.2916

Max Act: 3.0132. Min Act: -0.1700

Data Index: 8143365 (Open Web Text)

Max Activating Token Index: 419

Text #8

Max Range: 3.2916. Min Range: -3.2916

Max Act: 2.9722. Min Act: -0.1700

Data Index: 6347287 (Open Web Text)

Max Activating Token Index: 30

Text #9

Max Range: 3.2916. Min Range: -3.2916

Max Act: 2.9552. Min Act: -0.1700

Data Index: 5472334 (Open Web Text)

Max Activating Token Index: 494

Text #10

Max Range: 3.2916. Min Range: -3.2916

Max Act: 2.9454. Min Act: -0.1700

Data Index: 7337516 (Open Web Text)

Max Activating Token Index: 651

Text #11

Max Range: 3.2916. Min Range: -3.2916

Max Act: 2.9551. Min Act: -0.1700

Data Index: 491685 (Open Web Text)

Max Activating Token Index: 653

Text #12

Max Range: 3.2916. Min Range: -3.2916

Max Act: 2.9305. Min Act: -0.1700

Data Index: 2925643 (Open Web Text)

Max Activating Token Index: 472

Text #13

Max Range: 3.2916. Min Range: -3.2916

Max Act: 2.9376. Min Act: -0.1700

Data Index: 3564286 (Open Web Text)

Max Activating Token Index: 254

Text #14

Max Range: 3.2916. Min Range: -3.2916

Max Act: 2.9208. Min Act: -0.1700

Data Index: 2925690 (Open Web Text)

Max Activating Token Index: 305

Text #15

Max Range: 3.2916. Min Range: -3.2916

Max Act: 2.9134. Min Act: -0.1700

Data Index: 6951486 (Open Web Text)

Max Activating Token Index: 599

Text #16

Max Range: 3.2916. Min Range: -3.2916

Max Act: 2.9137. Min Act: -0.1700

Data Index: 4793906 (Open Web Text)

Max Activating Token Index: 173

Text #17

Max Range: 3.2916. Min Range: -3.2916

Max Act: 2.9315. Min Act: -0.1700

Data Index: 2773014 (Open Web Text)

Max Activating Token Index: 343

Text #18

Max Range: 3.2916. Min Range: -3.2916

Max Act: 2.9348. Min Act: -0.1700

Data Index: 2314288 (Open Web Text)

Max Activating Token Index: 433

Text #19

Max Range: 3.2916. Min Range: -3.2916

Max Act: 2.9074. Min Act: -0.1700

Data Index: 4365618 (Open Web Text)

Max Activating Token Index: 633