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

Dataset: Open Web Text

Neuron 410 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: 4.2797. Min Range: -4.2797

Max Act: 4.2797. Min Act: -0.1700

Data Index: 461186 (Open Web Text)

Max Activating Token Index: 894

Text #1

Max Range: 4.2797. Min Range: -4.2797

Max Act: 4.2421. Min Act: -0.1700

Data Index: 7650410 (Open Web Text)

Max Activating Token Index: 245

Text #2

Max Range: 4.2797. Min Range: -4.2797

Max Act: 4.1650. Min Act: -0.1700

Data Index: 5369422 (Open Web Text)

Max Activating Token Index: 673

Text #3

Max Range: 4.2797. Min Range: -4.2797

Max Act: 4.1852. Min Act: -0.1700

Data Index: 6359290 (Open Web Text)

Max Activating Token Index: 339

Text #4

Max Range: 4.2797. Min Range: -4.2797

Max Act: 4.1303. Min Act: -0.1700

Data Index: 8778733 (Open Web Text)

Max Activating Token Index: 770

Text #5

Max Range: 4.2797. Min Range: -4.2797

Max Act: 4.1394. Min Act: -0.1700

Data Index: 1566026 (Open Web Text)

Max Activating Token Index: 858

Text #6

Max Range: 4.2797. Min Range: -4.2797

Max Act: 4.1413. Min Act: -0.1700

Data Index: 103660 (Open Web Text)

Max Activating Token Index: 337

Text #7

Max Range: 4.2797. Min Range: -4.2797

Max Act: 4.1580. Min Act: -0.1700

Data Index: 5451259 (Open Web Text)

Max Activating Token Index: 727

Text #8

Max Range: 4.2797. Min Range: -4.2797

Max Act: 4.1242. Min Act: -0.1700

Data Index: 1355172 (Open Web Text)

Max Activating Token Index: 659

Text #9

Max Range: 4.2797. Min Range: -4.2797

Max Act: 4.1440. Min Act: -0.1700

Data Index: 5652860 (Open Web Text)

Max Activating Token Index: 600

Text #10

Max Range: 4.2797. Min Range: -4.2797

Max Act: 4.1250. Min Act: -0.1700

Data Index: 1049341 (Open Web Text)

Max Activating Token Index: 435

Text #11

Max Range: 4.2797. Min Range: -4.2797

Max Act: 4.1397. Min Act: -0.1700

Data Index: 5706257 (Open Web Text)

Max Activating Token Index: 44

Text #12

Max Range: 4.2797. Min Range: -4.2797

Max Act: 4.1122. Min Act: -0.1700

Data Index: 3032824 (Open Web Text)

Max Activating Token Index: 214

Text #13

Max Range: 4.2797. Min Range: -4.2797

Max Act: 4.1195. Min Act: -0.1700

Data Index: 2186536 (Open Web Text)

Max Activating Token Index: 662

Text #14

Max Range: 4.2797. Min Range: -4.2797

Max Act: 4.0924. Min Act: -0.1700

Data Index: 3069272 (Open Web Text)

Max Activating Token Index: 717

Text #15

Max Range: 4.2797. Min Range: -4.2797

Max Act: 4.0921. Min Act: -0.1700

Data Index: 1921271 (Open Web Text)

Max Activating Token Index: 994

Text #16

Max Range: 4.2797. Min Range: -4.2797

Max Act: 4.0671. Min Act: -0.1700

Data Index: 1319318 (Open Web Text)

Max Activating Token Index: 191

Text #17

Max Range: 4.2797. Min Range: -4.2797

Max Act: 4.0801. Min Act: -0.1700

Data Index: 1276437 (Open Web Text)

Max Activating Token Index: 260

Text #18

Max Range: 4.2797. Min Range: -4.2797

Max Act: 4.0755. Min Act: -0.1700

Data Index: 3390250 (Open Web Text)

Max Activating Token Index: 17

Text #19

Max Range: 4.2797. Min Range: -4.2797

Max Act: 4.0898. Min Act: -0.1700

Data Index: 5803670 (Open Web Text)

Max Activating Token Index: 678