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

Dataset: Open Web Text

Neuron 121 in Layer 1

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: 1.5092. Min Range: -1.5092

Max Act: 1.5092. Min Act: -0.1695

Data Index: 6583247 (Open Web Text)

Max Activating Token Index: 520

Text #1

Max Range: 1.5092. Min Range: -1.5092

Max Act: 1.4999. Min Act: -0.1676

Data Index: 1665925 (Open Web Text)

Max Activating Token Index: 467

Text #2

Max Range: 1.5092. Min Range: -1.5092

Max Act: 1.4904. Min Act: -0.1699

Data Index: 3732011 (Open Web Text)

Max Activating Token Index: 549

Text #3

Max Range: 1.5092. Min Range: -1.5092

Max Act: 1.4722. Min Act: -0.1665

Data Index: 1538524 (Open Web Text)

Max Activating Token Index: 234

Text #4

Max Range: 1.5092. Min Range: -1.5092

Max Act: 1.4719. Min Act: -0.1700

Data Index: 4206300 (Open Web Text)

Max Activating Token Index: 478

Text #5

Max Range: 1.5092. Min Range: -1.5092

Max Act: 1.4677. Min Act: -0.1700

Data Index: 6291738 (Open Web Text)

Max Activating Token Index: 184

Text #6

Max Range: 1.5092. Min Range: -1.5092

Max Act: 1.4756. Min Act: -0.1625

Data Index: 6118659 (Open Web Text)

Max Activating Token Index: 63

Text #7

Max Range: 1.5092. Min Range: -1.5092

Max Act: 1.4738. Min Act: -0.1700

Data Index: 7444274 (Open Web Text)

Max Activating Token Index: 694

Text #8

Max Range: 1.5092. Min Range: -1.5092

Max Act: 1.4615. Min Act: -0.1700

Data Index: 8687655 (Open Web Text)

Max Activating Token Index: 322

Text #9

Max Range: 1.5092. Min Range: -1.5092

Max Act: 1.4698. Min Act: -0.1699

Data Index: 873154 (Open Web Text)

Max Activating Token Index: 549

Text #10

Max Range: 1.5092. Min Range: -1.5092

Max Act: 1.4566. Min Act: -0.1696

Data Index: 1070850 (Open Web Text)

Max Activating Token Index: 791

Text #11

Max Range: 1.5092. Min Range: -1.5092

Max Act: 1.4517. Min Act: -0.1698

Data Index: 1239017 (Open Web Text)

Max Activating Token Index: 156

Text #12

Max Range: 1.5092. Min Range: -1.5092

Max Act: 1.4573. Min Act: -0.1700

Data Index: 1402231 (Open Web Text)

Max Activating Token Index: 550

Text #13

Max Range: 1.5092. Min Range: -1.5092

Max Act: 1.4503. Min Act: -0.1700

Data Index: 3048048 (Open Web Text)

Max Activating Token Index: 572

Text #14

Max Range: 1.5092. Min Range: -1.5092

Max Act: 1.4477. Min Act: -0.1688

Data Index: 7709182 (Open Web Text)

Max Activating Token Index: 692

Text #15

Max Range: 1.5092. Min Range: -1.5092

Max Act: 1.4575. Min Act: -0.1699

Data Index: 2390439 (Open Web Text)

Max Activating Token Index: 472

Text #16

Max Range: 1.5092. Min Range: -1.5092

Max Act: 1.4482. Min Act: -0.1699

Data Index: 1835848 (Open Web Text)

Max Activating Token Index: 699

Text #17

Max Range: 1.5092. Min Range: -1.5092

Max Act: 1.4477. Min Act: -0.1700

Data Index: 4790097 (Open Web Text)

Max Activating Token Index: 598

Text #18

Max Range: 1.5092. Min Range: -1.5092

Max Act: 1.4461. Min Act: -0.1699

Data Index: 2108941 (Open Web Text)

Max Activating Token Index: 739

Text #19

Max Range: 1.5092. Min Range: -1.5092

Max Act: 1.4457. Min Act: -0.1700

Data Index: 345930 (Open Web Text)

Max Activating Token Index: 84