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

Dataset: Open Web Text

Neuron 1776 in Layer 2

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: 4.9509. Min Range: -4.9509

Max Act: 4.9509. Min Act: -0.1700

Data Index: 2713020 (Open Web Text)

Max Activating Token Index: 631

Text #1

Max Range: 4.9509. Min Range: -4.9509

Max Act: 4.9209. Min Act: -0.1700

Data Index: 3250807 (Open Web Text)

Max Activating Token Index: 238

Text #2

Max Range: 4.9509. Min Range: -4.9509

Max Act: 4.8528. Min Act: -0.1700

Data Index: 113102 (Open Web Text)

Max Activating Token Index: 665

Text #3

Max Range: 4.9509. Min Range: -4.9509

Max Act: 4.8671. Min Act: -0.1700

Data Index: 2770634 (Open Web Text)

Max Activating Token Index: 1005

Text #4

Max Range: 4.9509. Min Range: -4.9509

Max Act: 4.8071. Min Act: -0.1700

Data Index: 4942062 (Open Web Text)

Max Activating Token Index: 406

Text #5

Max Range: 4.9509. Min Range: -4.9509

Max Act: 4.7829. Min Act: -0.1700

Data Index: 6130690 (Open Web Text)

Max Activating Token Index: 345

Text #6

Max Range: 4.9509. Min Range: -4.9509

Max Act: 4.7712. Min Act: -0.1700

Data Index: 7252322 (Open Web Text)

Max Activating Token Index: 567

Text #7

Max Range: 4.9509. Min Range: -4.9509

Max Act: 4.7391. Min Act: -0.1700

Data Index: 2878445 (Open Web Text)

Max Activating Token Index: 490

Text #8

Max Range: 4.9509. Min Range: -4.9509

Max Act: 4.7680. Min Act: -0.1700

Data Index: 1167032 (Open Web Text)

Max Activating Token Index: 455

Text #9

Max Range: 4.9509. Min Range: -4.9509

Max Act: 4.7719. Min Act: -0.1700

Data Index: 8570863 (Open Web Text)

Max Activating Token Index: 1022

Text #10

Max Range: 4.9509. Min Range: -4.9509

Max Act: 4.7406. Min Act: -0.1700

Data Index: 7021891 (Open Web Text)

Max Activating Token Index: 466

Text #11

Max Range: 4.9509. Min Range: -4.9509

Max Act: 4.7385. Min Act: -0.1700

Data Index: 4564052 (Open Web Text)

Max Activating Token Index: 580

Text #12

Max Range: 4.9509. Min Range: -4.9509

Max Act: 4.7655. Min Act: -0.1700

Data Index: 8422728 (Open Web Text)

Max Activating Token Index: 575

Text #13

Max Range: 4.9509. Min Range: -4.9509

Max Act: 4.6747. Min Act: -0.1700

Data Index: 3470200 (Open Web Text)

Max Activating Token Index: 905

Text #14

Max Range: 4.9509. Min Range: -4.9509

Max Act: 4.7374. Min Act: -0.1700

Data Index: 2091033 (Open Web Text)

Max Activating Token Index: 66

Text #15

Max Range: 4.9509. Min Range: -4.9509

Max Act: 4.7216. Min Act: -0.1700

Data Index: 8262328 (Open Web Text)

Max Activating Token Index: 918

Text #16

Max Range: 4.9509. Min Range: -4.9509

Max Act: 4.7278. Min Act: -0.1700

Data Index: 2620010 (Open Web Text)

Max Activating Token Index: 70

Text #17

Max Range: 4.9509. Min Range: -4.9509

Max Act: 4.7000. Min Act: -0.1699

Data Index: 5913626 (Open Web Text)

Max Activating Token Index: 444

Text #18

Max Range: 4.9509. Min Range: -4.9509

Max Act: 4.7561. Min Act: -0.1698

Data Index: 2329140 (Open Web Text)

Max Activating Token Index: 652

Text #19

Max Range: 4.9509. Min Range: -4.9509

Max Act: 4.7290. Min Act: -0.1700

Data Index: 271191 (Open Web Text)

Max Activating Token Index: 575