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

Dataset: Open Web Text

Neuron 1480 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: 4.8345. Min Range: -4.8345

Max Act: 4.8345. Min Act: -0.1700

Data Index: 4322682 (Open Web Text)

Max Activating Token Index: 500

Text #1

Max Range: 4.8345. Min Range: -4.8345

Max Act: 4.6604. Min Act: -0.1700

Data Index: 660093 (Open Web Text)

Max Activating Token Index: 480

Text #2

Max Range: 4.8345. Min Range: -4.8345

Max Act: 4.6697. Min Act: -0.1700

Data Index: 5220926 (Open Web Text)

Max Activating Token Index: 589

Text #3

Max Range: 4.8345. Min Range: -4.8345

Max Act: 4.7070. Min Act: -0.1700

Data Index: 5759397 (Open Web Text)

Max Activating Token Index: 452

Text #4

Max Range: 4.8345. Min Range: -4.8345

Max Act: 4.7417. Min Act: -0.1700

Data Index: 6596714 (Open Web Text)

Max Activating Token Index: 907

Text #5

Max Range: 4.8345. Min Range: -4.8345

Max Act: 4.6862. Min Act: -0.1700

Data Index: 713779 (Open Web Text)

Max Activating Token Index: 485

Text #6

Max Range: 4.8345. Min Range: -4.8345

Max Act: 4.7005. Min Act: -0.1700

Data Index: 230654 (Open Web Text)

Max Activating Token Index: 427

Text #7

Max Range: 4.8345. Min Range: -4.8345

Max Act: 4.6590. Min Act: -0.1700

Data Index: 2487794 (Open Web Text)

Max Activating Token Index: 307

Text #8

Max Range: 4.8345. Min Range: -4.8345

Max Act: 4.6702. Min Act: -0.1700

Data Index: 8227744 (Open Web Text)

Max Activating Token Index: 560

Text #9

Max Range: 4.8345. Min Range: -4.8345

Max Act: 4.6519. Min Act: -0.1700

Data Index: 5962091 (Open Web Text)

Max Activating Token Index: 667

Text #10

Max Range: 4.8345. Min Range: -4.8345

Max Act: 4.6770. Min Act: -0.1700

Data Index: 6560205 (Open Web Text)

Max Activating Token Index: 584

Text #11

Max Range: 4.8345. Min Range: -4.8345

Max Act: 4.6344. Min Act: -0.1700

Data Index: 6191252 (Open Web Text)

Max Activating Token Index: 988

Text #12

Max Range: 4.8345. Min Range: -4.8345

Max Act: 4.6480. Min Act: -0.1700

Data Index: 651345 (Open Web Text)

Max Activating Token Index: 980

Text #13

Max Range: 4.8345. Min Range: -4.8345

Max Act: 4.6350. Min Act: -0.1700

Data Index: 1595778 (Open Web Text)

Max Activating Token Index: 966

Text #14

Max Range: 4.8345. Min Range: -4.8345

Max Act: 4.6619. Min Act: -0.1700

Data Index: 3062067 (Open Web Text)

Max Activating Token Index: 190

Text #15

Max Range: 4.8345. Min Range: -4.8345

Max Act: 4.6480. Min Act: -0.1700

Data Index: 5966795 (Open Web Text)

Max Activating Token Index: 429

Text #16

Max Range: 4.8345. Min Range: -4.8345

Max Act: 4.6347. Min Act: -0.1700

Data Index: 2902107 (Open Web Text)

Max Activating Token Index: 582

Text #17

Max Range: 4.8345. Min Range: -4.8345

Max Act: 4.6705. Min Act: -0.1700

Data Index: 2700425 (Open Web Text)

Max Activating Token Index: 791

Text #18

Max Range: 4.8345. Min Range: -4.8345

Max Act: 4.6234. Min Act: -0.1700

Data Index: 5339654 (Open Web Text)

Max Activating Token Index: 383

Text #19

Max Range: 4.8345. Min Range: -4.8345

Max Act: 4.6276. Min Act: -0.1700

Data Index: 626607 (Open Web Text)

Max Activating Token Index: 641