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

Dataset: Open Web Text

Neuron 1787 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: 3.7398. Min Range: -3.7398

Max Act: 3.7398. Min Act: -0.1700

Data Index: 2629279 (Open Web Text)

Max Activating Token Index: 313

Text #1

Max Range: 3.7398. Min Range: -3.7398

Max Act: 3.6997. Min Act: -0.1700

Data Index: 3216520 (Open Web Text)

Max Activating Token Index: 48

Text #2

Max Range: 3.7398. Min Range: -3.7398

Max Act: 3.6907. Min Act: -0.1700

Data Index: 6855573 (Open Web Text)

Max Activating Token Index: 715

Text #3

Max Range: 3.7398. Min Range: -3.7398

Max Act: 3.6603. Min Act: -0.1700

Data Index: 4670872 (Open Web Text)

Max Activating Token Index: 537

Text #4

Max Range: 3.7398. Min Range: -3.7398

Max Act: 3.6134. Min Act: -0.1700

Data Index: 2955454 (Open Web Text)

Max Activating Token Index: 138

Text #5

Max Range: 3.7398. Min Range: -3.7398

Max Act: 3.5959. Min Act: -0.1700

Data Index: 1508744 (Open Web Text)

Max Activating Token Index: 161

Text #6

Max Range: 3.7398. Min Range: -3.7398

Max Act: 3.5674. Min Act: -0.1700

Data Index: 5898622 (Open Web Text)

Max Activating Token Index: 455

Text #7

Max Range: 3.7398. Min Range: -3.7398

Max Act: 3.5385. Min Act: -0.1700

Data Index: 2387901 (Open Web Text)

Max Activating Token Index: 197

Text #8

Max Range: 3.7398. Min Range: -3.7398

Max Act: 3.5528. Min Act: -0.1700

Data Index: 7364691 (Open Web Text)

Max Activating Token Index: 17

Text #9

Max Range: 3.7398. Min Range: -3.7398

Max Act: 3.5466. Min Act: -0.1700

Data Index: 1290020 (Open Web Text)

Max Activating Token Index: 152

Text #10

Max Range: 3.7398. Min Range: -3.7398

Max Act: 3.5608. Min Act: -0.1700

Data Index: 6522282 (Open Web Text)

Max Activating Token Index: 462

Text #11

Max Range: 3.7398. Min Range: -3.7398

Max Act: 3.5490. Min Act: -0.1700

Data Index: 6255526 (Open Web Text)

Max Activating Token Index: 305

Text #12

Max Range: 3.7398. Min Range: -3.7398

Max Act: 3.5387. Min Act: -0.1700

Data Index: 7616132 (Open Web Text)

Max Activating Token Index: 627

Text #13

Max Range: 3.7398. Min Range: -3.7398

Max Act: 3.5126. Min Act: -0.1700

Data Index: 3783053 (Open Web Text)

Max Activating Token Index: 692

Text #14

Max Range: 3.7398. Min Range: -3.7398

Max Act: 3.5615. Min Act: -0.1700

Data Index: 2608668 (Open Web Text)

Max Activating Token Index: 302

Text #15

Max Range: 3.7398. Min Range: -3.7398

Max Act: 3.5149. Min Act: -0.1700

Data Index: 3824392 (Open Web Text)

Max Activating Token Index: 408

Text #16

Max Range: 3.7398. Min Range: -3.7398

Max Act: 3.5250. Min Act: -0.1700

Data Index: 2158464 (Open Web Text)

Max Activating Token Index: 41

Text #17

Max Range: 3.7398. Min Range: -3.7398

Max Act: 3.5158. Min Act: -0.1700

Data Index: 5599406 (Open Web Text)

Max Activating Token Index: 267

Text #18

Max Range: 3.7398. Min Range: -3.7398

Max Act: 3.4954. Min Act: -0.1700

Data Index: 6184582 (Open Web Text)

Max Activating Token Index: 379

Text #19

Max Range: 3.7398. Min Range: -3.7398

Max Act: 3.4913. Min Act: -0.1700

Data Index: 3544655 (Open Web Text)

Max Activating Token Index: 189