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

Dataset: Open Web Text

Neuron 1087 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: 3.5693. Min Range: -3.5693

Max Act: 3.5693. Min Act: -0.1700

Data Index: 1599808 (Open Web Text)

Max Activating Token Index: 185

Text #1

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.5263. Min Act: -0.1700

Data Index: 2205202 (Open Web Text)

Max Activating Token Index: 452

Text #2

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.4631. Min Act: -0.1700

Data Index: 6552130 (Open Web Text)

Max Activating Token Index: 882

Text #3

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.4382. Min Act: -0.1700

Data Index: 1035776 (Open Web Text)

Max Activating Token Index: 932

Text #4

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.4115. Min Act: -0.1700

Data Index: 7355131 (Open Web Text)

Max Activating Token Index: 453

Text #5

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.4173. Min Act: -0.1700

Data Index: 1471846 (Open Web Text)

Max Activating Token Index: 198

Text #6

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.4242. Min Act: -0.1700

Data Index: 5017457 (Open Web Text)

Max Activating Token Index: 348

Text #7

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.4070. Min Act: -0.1700

Data Index: 6012889 (Open Web Text)

Max Activating Token Index: 698

Text #8

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.4042. Min Act: -0.1700

Data Index: 3070543 (Open Web Text)

Max Activating Token Index: 742

Text #9

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.4116. Min Act: -0.1700

Data Index: 2547814 (Open Web Text)

Max Activating Token Index: 788

Text #10

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.4200. Min Act: -0.1700

Data Index: 245373 (Open Web Text)

Max Activating Token Index: 807

Text #11

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.3791. Min Act: -0.1700

Data Index: 4963956 (Open Web Text)

Max Activating Token Index: 459

Text #12

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.3904. Min Act: -0.1700

Data Index: 2809295 (Open Web Text)

Max Activating Token Index: 841

Text #13

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.3977. Min Act: -0.1700

Data Index: 3396410 (Open Web Text)

Max Activating Token Index: 362

Text #14

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.3802. Min Act: -0.1700

Data Index: 2572729 (Open Web Text)

Max Activating Token Index: 691

Text #15

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.3781. Min Act: -0.1700

Data Index: 6233774 (Open Web Text)

Max Activating Token Index: 405

Text #16

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.3694. Min Act: -0.1700

Data Index: 8377450 (Open Web Text)

Max Activating Token Index: 293

Text #17

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.3607. Min Act: -0.1700

Data Index: 6886490 (Open Web Text)

Max Activating Token Index: 865

Text #18

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.3676. Min Act: -0.1700

Data Index: 8621353 (Open Web Text)

Max Activating Token Index: 334

Text #19

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.3641. Min Act: -0.1700

Data Index: 7052841 (Open Web Text)

Max Activating Token Index: 438