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

Dataset: Open Web Text

Neuron 1923 in Layer 4

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: 3.9265. Min Range: -3.9265

Max Act: 3.9265. Min Act: -0.1700

Data Index: 6192623 (Open Web Text)

Max Activating Token Index: 450

Text #1

Max Range: 3.9265. Min Range: -3.9265

Max Act: 3.8622. Min Act: -0.1700

Data Index: 7202393 (Open Web Text)

Max Activating Token Index: 571

Text #2

Max Range: 3.9265. Min Range: -3.9265

Max Act: 3.8650. Min Act: -0.1700

Data Index: 7202394 (Open Web Text)

Max Activating Token Index: 448

Text #3

Max Range: 3.9265. Min Range: -3.9265

Max Act: 3.8758. Min Act: -0.1700

Data Index: 4006940 (Open Web Text)

Max Activating Token Index: 611

Text #4

Max Range: 3.9265. Min Range: -3.9265

Max Act: 3.8644. Min Act: -0.1700

Data Index: 3119294 (Open Web Text)

Max Activating Token Index: 588

Text #5

Max Range: 3.9265. Min Range: -3.9265

Max Act: 3.8345. Min Act: -0.1700

Data Index: 2134823 (Open Web Text)

Max Activating Token Index: 546

Text #6

Max Range: 3.9265. Min Range: -3.9265

Max Act: 3.8196. Min Act: -0.1700

Data Index: 3582233 (Open Web Text)

Max Activating Token Index: 531

Text #7

Max Range: 3.9265. Min Range: -3.9265

Max Act: 3.8506. Min Act: -0.1700

Data Index: 7214456 (Open Web Text)

Max Activating Token Index: 628

Text #8

Max Range: 3.9265. Min Range: -3.9265

Max Act: 3.8260. Min Act: -0.1700

Data Index: 7958104 (Open Web Text)

Max Activating Token Index: 663

Text #9

Max Range: 3.9265. Min Range: -3.9265

Max Act: 3.8216. Min Act: -0.1700

Data Index: 1973013 (Open Web Text)

Max Activating Token Index: 95

Text #10

Max Range: 3.9265. Min Range: -3.9265

Max Act: 3.8091. Min Act: -0.1700

Data Index: 310908 (Open Web Text)

Max Activating Token Index: 796

Text #11

Max Range: 3.9265. Min Range: -3.9265

Max Act: 3.7936. Min Act: -0.1700

Data Index: 6894207 (Open Web Text)

Max Activating Token Index: 414

Text #12

Max Range: 3.9265. Min Range: -3.9265

Max Act: 3.8111. Min Act: -0.1700

Data Index: 5442821 (Open Web Text)

Max Activating Token Index: 803

Text #13

Max Range: 3.9265. Min Range: -3.9265

Max Act: 3.7937. Min Act: -0.1700

Data Index: 457556 (Open Web Text)

Max Activating Token Index: 82

Text #14

Max Range: 3.9265. Min Range: -3.9265

Max Act: 3.8034. Min Act: -0.1700

Data Index: 2272812 (Open Web Text)

Max Activating Token Index: 637

Text #15

Max Range: 3.9265. Min Range: -3.9265

Max Act: 3.7922. Min Act: -0.1700

Data Index: 8698385 (Open Web Text)

Max Activating Token Index: 509

Text #16

Max Range: 3.9265. Min Range: -3.9265

Max Act: 3.7466. Min Act: -0.1700

Data Index: 8558921 (Open Web Text)

Max Activating Token Index: 391

Text #17

Max Range: 3.9265. Min Range: -3.9265

Max Act: 3.7660. Min Act: -0.1700

Data Index: 6035939 (Open Web Text)

Max Activating Token Index: 289

Text #18

Max Range: 3.9265. Min Range: -3.9265

Max Act: 3.7584. Min Act: -0.1700

Data Index: 2618773 (Open Web Text)

Max Activating Token Index: 756

Text #19

Max Range: 3.9265. Min Range: -3.9265

Max Act: 3.7826. Min Act: -0.1700

Data Index: 5902773 (Open Web Text)

Max Activating Token Index: 88