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

Dataset: Open Web Text

Neuron 2344 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: 3.0740. Min Range: -3.0740

Max Act: 3.0740. Min Act: -0.1700

Data Index: 7607612 (Open Web Text)

Max Activating Token Index: 448

Text #1

Max Range: 3.0740. Min Range: -3.0740

Max Act: 3.0518. Min Act: -0.1700

Data Index: 766114 (Open Web Text)

Max Activating Token Index: 134

Text #2

Max Range: 3.0740. Min Range: -3.0740

Max Act: 3.0611. Min Act: -0.1700

Data Index: 7194840 (Open Web Text)

Max Activating Token Index: 869

Text #3

Max Range: 3.0740. Min Range: -3.0740

Max Act: 3.0648. Min Act: -0.1700

Data Index: 7412669 (Open Web Text)

Max Activating Token Index: 701

Text #4

Max Range: 3.0740. Min Range: -3.0740

Max Act: 3.0513. Min Act: -0.1700

Data Index: 8147424 (Open Web Text)

Max Activating Token Index: 229

Text #5

Max Range: 3.0740. Min Range: -3.0740

Max Act: 3.0158. Min Act: -0.1700

Data Index: 8235266 (Open Web Text)

Max Activating Token Index: 590

Text #6

Max Range: 3.0740. Min Range: -3.0740

Max Act: 3.0590. Min Act: -0.1700

Data Index: 7364766 (Open Web Text)

Max Activating Token Index: 265

Text #7

Max Range: 3.0740. Min Range: -3.0740

Max Act: 3.0253. Min Act: -0.1700

Data Index: 3351827 (Open Web Text)

Max Activating Token Index: 59

Text #8

Max Range: 3.0740. Min Range: -3.0740

Max Act: 3.0229. Min Act: -0.1700

Data Index: 6179914 (Open Web Text)

Max Activating Token Index: 834

Text #9

Max Range: 3.0740. Min Range: -3.0740

Max Act: 2.9962. Min Act: -0.1700

Data Index: 7634802 (Open Web Text)

Max Activating Token Index: 10

Text #10

Max Range: 3.0740. Min Range: -3.0740

Max Act: 2.9624. Min Act: -0.1700

Data Index: 5740986 (Open Web Text)

Max Activating Token Index: 634

Text #11

Max Range: 3.0740. Min Range: -3.0740

Max Act: 3.0265. Min Act: -0.1700

Data Index: 1389430 (Open Web Text)

Max Activating Token Index: 363

Text #12

Max Range: 3.0740. Min Range: -3.0740

Max Act: 2.9811. Min Act: -0.1700

Data Index: 1988556 (Open Web Text)

Max Activating Token Index: 610

Text #13

Max Range: 3.0740. Min Range: -3.0740

Max Act: 2.9513. Min Act: -0.1700

Data Index: 5699629 (Open Web Text)

Max Activating Token Index: 485

Text #14

Max Range: 3.0740. Min Range: -3.0740

Max Act: 2.9955. Min Act: -0.1700

Data Index: 3887679 (Open Web Text)

Max Activating Token Index: 161

Text #15

Max Range: 3.0740. Min Range: -3.0740

Max Act: 2.9720. Min Act: -0.1700

Data Index: 375098 (Open Web Text)

Max Activating Token Index: 138

Text #16

Max Range: 3.0740. Min Range: -3.0740

Max Act: 2.9591. Min Act: -0.1700

Data Index: 4276238 (Open Web Text)

Max Activating Token Index: 229

Text #17

Max Range: 3.0740. Min Range: -3.0740

Max Act: 2.9656. Min Act: -0.1700

Data Index: 4428388 (Open Web Text)

Max Activating Token Index: 832

Text #18

Max Range: 3.0740. Min Range: -3.0740

Max Act: 2.9694. Min Act: -0.1700

Data Index: 2879909 (Open Web Text)

Max Activating Token Index: 888

Text #19

Max Range: 3.0740. Min Range: -3.0740

Max Act: 2.9531. Min Act: -0.1700

Data Index: 1950590 (Open Web Text)

Max Activating Token Index: 588