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

Dataset: Open Web Text

Neuron 2737 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: 4.2279. Min Range: -4.2279

Max Act: 4.2279. Min Act: -0.1700

Data Index: 2429818 (Open Web Text)

Max Activating Token Index: 811

Text #1

Max Range: 4.2279. Min Range: -4.2279

Max Act: 3.8446. Min Act: -0.1700

Data Index: 3847166 (Open Web Text)

Max Activating Token Index: 600

Text #2

Max Range: 4.2279. Min Range: -4.2279

Max Act: 3.9057. Min Act: -0.1700

Data Index: 944442 (Open Web Text)

Max Activating Token Index: 554

Text #3

Max Range: 4.2279. Min Range: -4.2279

Max Act: 3.8586. Min Act: -0.1700

Data Index: 5417331 (Open Web Text)

Max Activating Token Index: 801

Text #4

Max Range: 4.2279. Min Range: -4.2279

Max Act: 3.7881. Min Act: -0.1700

Data Index: 5533372 (Open Web Text)

Max Activating Token Index: 144

Text #5

Max Range: 4.2279. Min Range: -4.2279

Max Act: 3.7592. Min Act: -0.1700

Data Index: 1376638 (Open Web Text)

Max Activating Token Index: 296

Text #6

Max Range: 4.2279. Min Range: -4.2279

Max Act: 3.7339. Min Act: -0.1700

Data Index: 5569583 (Open Web Text)

Max Activating Token Index: 29

Text #7

Max Range: 4.2279. Min Range: -4.2279

Max Act: 3.7419. Min Act: -0.1700

Data Index: 1834383 (Open Web Text)

Max Activating Token Index: 931

Text #8

Max Range: 4.2279. Min Range: -4.2279

Max Act: 3.7425. Min Act: -0.1700

Data Index: 2059032 (Open Web Text)

Max Activating Token Index: 243

Text #9

Max Range: 4.2279. Min Range: -4.2279

Max Act: 3.6795. Min Act: -0.1700

Data Index: 5229103 (Open Web Text)

Max Activating Token Index: 254

Text #10

Max Range: 4.2279. Min Range: -4.2279

Max Act: 3.7011. Min Act: -0.1700

Data Index: 8276562 (Open Web Text)

Max Activating Token Index: 820

Text #11

Max Range: 4.2279. Min Range: -4.2279

Max Act: 3.6560. Min Act: -0.1700

Data Index: 3804917 (Open Web Text)

Max Activating Token Index: 135

Text #12

Max Range: 4.2279. Min Range: -4.2279

Max Act: 3.7163. Min Act: -0.1700

Data Index: 4679981 (Open Web Text)

Max Activating Token Index: 358

Text #13

Max Range: 4.2279. Min Range: -4.2279

Max Act: 3.6974. Min Act: -0.1700

Data Index: 7546792 (Open Web Text)

Max Activating Token Index: 403

Text #14

Max Range: 4.2279. Min Range: -4.2279

Max Act: 3.6742. Min Act: -0.1700

Data Index: 7082900 (Open Web Text)

Max Activating Token Index: 154

Text #15

Max Range: 4.2279. Min Range: -4.2279

Max Act: 3.6531. Min Act: -0.1700

Data Index: 3886693 (Open Web Text)

Max Activating Token Index: 629

Text #16

Max Range: 4.2279. Min Range: -4.2279

Max Act: 3.6754. Min Act: -0.1700

Data Index: 3452210 (Open Web Text)

Max Activating Token Index: 502

Text #17

Max Range: 4.2279. Min Range: -4.2279

Max Act: 3.6442. Min Act: -0.1700

Data Index: 5056797 (Open Web Text)

Max Activating Token Index: 979

Text #18

Max Range: 4.2279. Min Range: -4.2279

Max Act: 3.6269. Min Act: -0.1700

Data Index: 5088273 (Open Web Text)

Max Activating Token Index: 418

Text #19

Max Range: 4.2279. Min Range: -4.2279

Max Act: 3.6074. Min Act: -0.1700

Data Index: 1493294 (Open Web Text)

Max Activating Token Index: 1005