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

Dataset: Open Web Text

Neuron 1050 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: 3.4151. Min Range: -3.4151

Max Act: 3.4151. Min Act: -0.1700

Data Index: 8522087 (Open Web Text)

Max Activating Token Index: 858

Text #1

Max Range: 3.4151. Min Range: -3.4151

Max Act: 3.3689. Min Act: -0.1700

Data Index: 5750490 (Open Web Text)

Max Activating Token Index: 685

Text #2

Max Range: 3.4151. Min Range: -3.4151

Max Act: 3.2775. Min Act: -0.1700

Data Index: 5442446 (Open Web Text)

Max Activating Token Index: 764

Text #3

Max Range: 3.4151. Min Range: -3.4151

Max Act: 3.2334. Min Act: -0.1700

Data Index: 6961211 (Open Web Text)

Max Activating Token Index: 637

Text #4

Max Range: 3.4151. Min Range: -3.4151

Max Act: 3.2108. Min Act: -0.1700

Data Index: 5663477 (Open Web Text)

Max Activating Token Index: 575

Text #5

Max Range: 3.4151. Min Range: -3.4151

Max Act: 3.2050. Min Act: -0.1700

Data Index: 94580 (Open Web Text)

Max Activating Token Index: 540

Text #6

Max Range: 3.4151. Min Range: -3.4151

Max Act: 3.1967. Min Act: -0.1700

Data Index: 3621460 (Open Web Text)

Max Activating Token Index: 393

Text #7

Max Range: 3.4151. Min Range: -3.4151

Max Act: 3.1707. Min Act: -0.1700

Data Index: 4670114 (Open Web Text)

Max Activating Token Index: 923

Text #8

Max Range: 3.4151. Min Range: -3.4151

Max Act: 3.1730. Min Act: -0.1700

Data Index: 2813961 (Open Web Text)

Max Activating Token Index: 585

Text #9

Max Range: 3.4151. Min Range: -3.4151

Max Act: 3.1426. Min Act: -0.1700

Data Index: 7083415 (Open Web Text)

Max Activating Token Index: 654

Text #10

Max Range: 3.4151. Min Range: -3.4151

Max Act: 3.1560. Min Act: -0.1700

Data Index: 6058044 (Open Web Text)

Max Activating Token Index: 358

Text #11

Max Range: 3.4151. Min Range: -3.4151

Max Act: 3.1390. Min Act: -0.1700

Data Index: 3209614 (Open Web Text)

Max Activating Token Index: 371

Text #12

Max Range: 3.4151. Min Range: -3.4151

Max Act: 3.1550. Min Act: -0.1700

Data Index: 1976375 (Open Web Text)

Max Activating Token Index: 584

Text #13

Max Range: 3.4151. Min Range: -3.4151

Max Act: 3.1558. Min Act: -0.1700

Data Index: 5036160 (Open Web Text)

Max Activating Token Index: 438

Text #14

Max Range: 3.4151. Min Range: -3.4151

Max Act: 3.1537. Min Act: -0.1700

Data Index: 5501287 (Open Web Text)

Max Activating Token Index: 835

Text #15

Max Range: 3.4151. Min Range: -3.4151

Max Act: 3.1271. Min Act: -0.1700

Data Index: 546088 (Open Web Text)

Max Activating Token Index: 48

Text #16

Max Range: 3.4151. Min Range: -3.4151

Max Act: 3.1242. Min Act: -0.1700

Data Index: 8485877 (Open Web Text)

Max Activating Token Index: 1019

Text #17

Max Range: 3.4151. Min Range: -3.4151

Max Act: 3.1367. Min Act: -0.1700

Data Index: 5086519 (Open Web Text)

Max Activating Token Index: 1013

Text #18

Max Range: 3.4151. Min Range: -3.4151

Max Act: 3.1428. Min Act: -0.1700

Data Index: 6981990 (Open Web Text)

Max Activating Token Index: 493

Text #19

Max Range: 3.4151. Min Range: -3.4151

Max Act: 3.1119. Min Act: -0.1700

Data Index: 4686812 (Open Web Text)

Max Activating Token Index: 546