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

Dataset: Open Web Text

Neuron 278 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: 4.7667. Min Range: -4.7667

Max Act: 4.7667. Min Act: -0.1700

Data Index: 8368190 (Open Web Text)

Max Activating Token Index: 154

Text #1

Max Range: 4.7667. Min Range: -4.7667

Max Act: 4.7333. Min Act: -0.1700

Data Index: 3490964 (Open Web Text)

Max Activating Token Index: 478

Text #2

Max Range: 4.7667. Min Range: -4.7667

Max Act: 4.6349. Min Act: -0.1700

Data Index: 360869 (Open Web Text)

Max Activating Token Index: 58

Text #3

Max Range: 4.7667. Min Range: -4.7667

Max Act: 4.6504. Min Act: -0.1700

Data Index: 1656064 (Open Web Text)

Max Activating Token Index: 187

Text #4

Max Range: 4.7667. Min Range: -4.7667

Max Act: 4.6639. Min Act: -0.1700

Data Index: 7374691 (Open Web Text)

Max Activating Token Index: 278

Text #5

Max Range: 4.7667. Min Range: -4.7667

Max Act: 4.6466. Min Act: -0.1700

Data Index: 563152 (Open Web Text)

Max Activating Token Index: 780

Text #6

Max Range: 4.7667. Min Range: -4.7667

Max Act: 4.6744. Min Act: -0.1700

Data Index: 4490668 (Open Web Text)

Max Activating Token Index: 178

Text #7

Max Range: 4.7667. Min Range: -4.7667

Max Act: 4.6142. Min Act: -0.1700

Data Index: 6209958 (Open Web Text)

Max Activating Token Index: 310

Text #8

Max Range: 4.7667. Min Range: -4.7667

Max Act: 4.6329. Min Act: -0.1700

Data Index: 6255257 (Open Web Text)

Max Activating Token Index: 75

Text #9

Max Range: 4.7667. Min Range: -4.7667

Max Act: 4.6222. Min Act: -0.1700

Data Index: 166071 (Open Web Text)

Max Activating Token Index: 237

Text #10

Max Range: 4.7667. Min Range: -4.7667

Max Act: 4.5933. Min Act: -0.1700

Data Index: 3483802 (Open Web Text)

Max Activating Token Index: 369

Text #11

Max Range: 4.7667. Min Range: -4.7667

Max Act: 4.5779. Min Act: -0.1700

Data Index: 4967099 (Open Web Text)

Max Activating Token Index: 572

Text #12

Max Range: 4.7667. Min Range: -4.7667

Max Act: 4.5848. Min Act: -0.1700

Data Index: 7757217 (Open Web Text)

Max Activating Token Index: 132

Text #13

Max Range: 4.7667. Min Range: -4.7667

Max Act: 4.5735. Min Act: -0.1700

Data Index: 4203515 (Open Web Text)

Max Activating Token Index: 604

Text #14

Max Range: 4.7667. Min Range: -4.7667

Max Act: 4.6000. Min Act: -0.1700

Data Index: 3664435 (Open Web Text)

Max Activating Token Index: 111

Text #15

Max Range: 4.7667. Min Range: -4.7667

Max Act: 4.6037. Min Act: -0.1700

Data Index: 5699446 (Open Web Text)

Max Activating Token Index: 716

Text #16

Max Range: 4.7667. Min Range: -4.7667

Max Act: 4.5618. Min Act: -0.1700

Data Index: 4528564 (Open Web Text)

Max Activating Token Index: 451

Text #17

Max Range: 4.7667. Min Range: -4.7667

Max Act: 4.5414. Min Act: -0.1700

Data Index: 7214421 (Open Web Text)

Max Activating Token Index: 509

Text #18

Max Range: 4.7667. Min Range: -4.7667

Max Act: 4.5122. Min Act: -0.1700

Data Index: 7016228 (Open Web Text)

Max Activating Token Index: 965

Text #19

Max Range: 4.7667. Min Range: -4.7667

Max Act: 4.5176. Min Act: -0.1700

Data Index: 5501754 (Open Web Text)

Max Activating Token Index: 61