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

Dataset: Open Web Text

Neuron 1921 in Layer 3

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: 4.8820. Min Range: -4.8820

Max Act: 4.8820. Min Act: -0.1700

Data Index: 6342282 (Open Web Text)

Max Activating Token Index: 58

Text #1

Max Range: 4.8820. Min Range: -4.8820

Max Act: 4.7761. Min Act: -0.1700

Data Index: 7818784 (Open Web Text)

Max Activating Token Index: 327

Text #2

Max Range: 4.8820. Min Range: -4.8820

Max Act: 4.8364. Min Act: -0.1700

Data Index: 3679592 (Open Web Text)

Max Activating Token Index: 795

Text #3

Max Range: 4.8820. Min Range: -4.8820

Max Act: 4.7398. Min Act: -0.1700

Data Index: 3294873 (Open Web Text)

Max Activating Token Index: 194

Text #4

Max Range: 4.8820. Min Range: -4.8820

Max Act: 4.7860. Min Act: -0.1700

Data Index: 4356386 (Open Web Text)

Max Activating Token Index: 478

Text #5

Max Range: 4.8820. Min Range: -4.8820

Max Act: 4.6940. Min Act: -0.1700

Data Index: 4072941 (Open Web Text)

Max Activating Token Index: 589

Text #6

Max Range: 4.8820. Min Range: -4.8820

Max Act: 4.6743. Min Act: -0.1699

Data Index: 1133736 (Open Web Text)

Max Activating Token Index: 801

Text #7

Max Range: 4.8820. Min Range: -4.8820

Max Act: 4.7299. Min Act: -0.1700

Data Index: 140503 (Open Web Text)

Max Activating Token Index: 664

Text #8

Max Range: 4.8820. Min Range: -4.8820

Max Act: 4.7236. Min Act: -0.1700

Data Index: 5202155 (Open Web Text)

Max Activating Token Index: 85

Text #9

Max Range: 4.8820. Min Range: -4.8820

Max Act: 4.7068. Min Act: -0.1700

Data Index: 2703350 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 4.8820. Min Range: -4.8820

Max Act: 4.6498. Min Act: -0.1700

Data Index: 3150147 (Open Web Text)

Max Activating Token Index: 271

Text #11

Max Range: 4.8820. Min Range: -4.8820

Max Act: 4.6311. Min Act: -0.1700

Data Index: 6473426 (Open Web Text)

Max Activating Token Index: 977

Text #12

Max Range: 4.8820. Min Range: -4.8820

Max Act: 4.5757. Min Act: -0.1700

Data Index: 5430678 (Open Web Text)

Max Activating Token Index: 1017

Text #13

Max Range: 4.8820. Min Range: -4.8820

Max Act: 4.6034. Min Act: -0.1700

Data Index: 5973814 (Open Web Text)

Max Activating Token Index: 499

Text #14

Max Range: 4.8820. Min Range: -4.8820

Max Act: 4.7066. Min Act: -0.1700

Data Index: 3068746 (Open Web Text)

Max Activating Token Index: 643

Text #15

Max Range: 4.8820. Min Range: -4.8820

Max Act: 4.7408. Min Act: -0.1700

Data Index: 2696319 (Open Web Text)

Max Activating Token Index: 728

Text #16

Max Range: 4.8820. Min Range: -4.8820

Max Act: 4.4613. Min Act: -0.1700

Data Index: 5246255 (Open Web Text)

Max Activating Token Index: 787

Text #17

Max Range: 4.8820. Min Range: -4.8820

Max Act: 4.6588. Min Act: -0.1700

Data Index: 697783 (Open Web Text)

Max Activating Token Index: 621

Text #18

Max Range: 4.8820. Min Range: -4.8820

Max Act: 4.5315. Min Act: -0.1700

Data Index: 5812329 (Open Web Text)

Max Activating Token Index: 206

Text #19

Max Range: 4.8820. Min Range: -4.8820

Max Act: 4.5457. Min Act: -0.1700

Data Index: 3407685 (Open Web Text)

Max Activating Token Index: 747