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

Dataset: Open Web Text

Neuron 193 in Layer 5

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: 3.2615. Min Range: -3.2615

Max Act: 3.2615. Min Act: -0.1700

Data Index: 1673217 (Open Web Text)

Max Activating Token Index: 175

Text #1

Max Range: 3.2615. Min Range: -3.2615

Max Act: 3.2614. Min Act: -0.1700

Data Index: 7479714 (Open Web Text)

Max Activating Token Index: 445

Text #2

Max Range: 3.2615. Min Range: -3.2615

Max Act: 3.1551. Min Act: -0.1700

Data Index: 2648289 (Open Web Text)

Max Activating Token Index: 361

Text #3

Max Range: 3.2615. Min Range: -3.2615

Max Act: 3.1243. Min Act: -0.1700

Data Index: 4346474 (Open Web Text)

Max Activating Token Index: 940

Text #4

Max Range: 3.2615. Min Range: -3.2615

Max Act: 3.1175. Min Act: -0.1700

Data Index: 2803694 (Open Web Text)

Max Activating Token Index: 475

Text #5

Max Range: 3.2615. Min Range: -3.2615

Max Act: 3.1255. Min Act: -0.1700

Data Index: 6409900 (Open Web Text)

Max Activating Token Index: 892

Text #6

Max Range: 3.2615. Min Range: -3.2615

Max Act: 3.0890. Min Act: -0.1700

Data Index: 4677409 (Open Web Text)

Max Activating Token Index: 917

Text #7

Max Range: 3.2615. Min Range: -3.2615

Max Act: 3.0892. Min Act: -0.1700

Data Index: 6997804 (Open Web Text)

Max Activating Token Index: 900

Text #8

Max Range: 3.2615. Min Range: -3.2615

Max Act: 3.0853. Min Act: -0.1700

Data Index: 4952690 (Open Web Text)

Max Activating Token Index: 120

Text #9

Max Range: 3.2615. Min Range: -3.2615

Max Act: 3.0856. Min Act: -0.1700

Data Index: 4047936 (Open Web Text)

Max Activating Token Index: 577

Text #10

Max Range: 3.2615. Min Range: -3.2615

Max Act: 3.0756. Min Act: -0.1700

Data Index: 5235443 (Open Web Text)

Max Activating Token Index: 654

Text #11

Max Range: 3.2615. Min Range: -3.2615

Max Act: 3.0856. Min Act: -0.1700

Data Index: 2664465 (Open Web Text)

Max Activating Token Index: 161

Text #12

Max Range: 3.2615. Min Range: -3.2615

Max Act: 3.0935. Min Act: -0.1700

Data Index: 7977049 (Open Web Text)

Max Activating Token Index: 1022

Text #13

Max Range: 3.2615. Min Range: -3.2615

Max Act: 3.0858. Min Act: -0.1700

Data Index: 8559915 (Open Web Text)

Max Activating Token Index: 33

Text #14

Max Range: 3.2615. Min Range: -3.2615

Max Act: 3.0619. Min Act: -0.1700

Data Index: 1969571 (Open Web Text)

Max Activating Token Index: 171

Text #15

Max Range: 3.2615. Min Range: -3.2615

Max Act: 3.0781. Min Act: -0.1700

Data Index: 6474087 (Open Web Text)

Max Activating Token Index: 548

Text #16

Max Range: 3.2615. Min Range: -3.2615

Max Act: 3.0678. Min Act: -0.1700

Data Index: 8469882 (Open Web Text)

Max Activating Token Index: 569

Text #17

Max Range: 3.2615. Min Range: -3.2615

Max Act: 3.0572. Min Act: -0.1700

Data Index: 436886 (Open Web Text)

Max Activating Token Index: 844

Text #18

Max Range: 3.2615. Min Range: -3.2615

Max Act: 3.0570. Min Act: -0.1700

Data Index: 4266991 (Open Web Text)

Max Activating Token Index: 82

Text #19

Max Range: 3.2615. Min Range: -3.2615

Max Act: 3.0444. Min Act: -0.1700

Data Index: 6997805 (Open Web Text)

Max Activating Token Index: 310