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

Dataset: Open Web Text

Neuron 2576 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: 1.7684. Min Range: -1.7684

Max Act: 1.7684. Min Act: -0.1700

Data Index: 7681244 (Open Web Text)

Max Activating Token Index: 339

Text #1

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.7349. Min Act: -0.1699

Data Index: 4397195 (Open Web Text)

Max Activating Token Index: 260

Text #2

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.7299. Min Act: -0.1697

Data Index: 3077876 (Open Web Text)

Max Activating Token Index: 184

Text #3

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.7152. Min Act: -0.1696

Data Index: 6854565 (Open Web Text)

Max Activating Token Index: 426

Text #4

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.7036. Min Act: -0.1699

Data Index: 4115867 (Open Web Text)

Max Activating Token Index: 342

Text #5

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.7059. Min Act: -0.1700

Data Index: 6729986 (Open Web Text)

Max Activating Token Index: 868

Text #6

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.7019. Min Act: -0.1700

Data Index: 6463000 (Open Web Text)

Max Activating Token Index: 989

Text #7

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.7028. Min Act: -0.1697

Data Index: 6270455 (Open Web Text)

Max Activating Token Index: 296

Text #8

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.6956. Min Act: -0.1700

Data Index: 2857911 (Open Web Text)

Max Activating Token Index: 686

Text #9

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.6886. Min Act: -0.1700

Data Index: 175778 (Open Web Text)

Max Activating Token Index: 448

Text #10

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.7000. Min Act: -0.1700

Data Index: 8391984 (Open Web Text)

Max Activating Token Index: 620

Text #11

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.6962. Min Act: -0.1699

Data Index: 2759834 (Open Web Text)

Max Activating Token Index: 661

Text #12

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.7025. Min Act: -0.1700

Data Index: 1222618 (Open Web Text)

Max Activating Token Index: 575

Text #13

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.6913. Min Act: -0.1700

Data Index: 5325015 (Open Web Text)

Max Activating Token Index: 543

Text #14

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.6870. Min Act: -0.1697

Data Index: 6674228 (Open Web Text)

Max Activating Token Index: 164

Text #15

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.6909. Min Act: -0.1700

Data Index: 7404493 (Open Web Text)

Max Activating Token Index: 385

Text #16

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.6895. Min Act: -0.1697

Data Index: 952804 (Open Web Text)

Max Activating Token Index: 671

Text #17

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.6831. Min Act: -0.1700

Data Index: 2405248 (Open Web Text)

Max Activating Token Index: 670

Text #18

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.6792. Min Act: -0.1700

Data Index: 5106070 (Open Web Text)

Max Activating Token Index: 567

Text #19

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.6914. Min Act: -0.1700

Data Index: 2205152 (Open Web Text)

Max Activating Token Index: 480