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

Dataset: Open Web Text

Neuron 2049 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: 2.9301. Min Range: -2.9301

Max Act: 2.9301. Min Act: -0.1700

Data Index: 1558565 (Open Web Text)

Max Activating Token Index: 574

Text #1

Max Range: 2.9301. Min Range: -2.9301

Max Act: 2.8701. Min Act: -0.1700

Data Index: 200697 (Open Web Text)

Max Activating Token Index: 651

Text #2

Max Range: 2.9301. Min Range: -2.9301

Max Act: 2.8652. Min Act: -0.1700

Data Index: 200695 (Open Web Text)

Max Activating Token Index: 891

Text #3

Max Range: 2.9301. Min Range: -2.9301

Max Act: 2.8430. Min Act: -0.1700

Data Index: 78272 (Open Web Text)

Max Activating Token Index: 95

Text #4

Max Range: 2.9301. Min Range: -2.9301

Max Act: 2.8421. Min Act: -0.1700

Data Index: 6127605 (Open Web Text)

Max Activating Token Index: 723

Text #5

Max Range: 2.9301. Min Range: -2.9301

Max Act: 2.8460. Min Act: -0.1700

Data Index: 7100146 (Open Web Text)

Max Activating Token Index: 606

Text #6

Max Range: 2.9301. Min Range: -2.9301

Max Act: 2.8220. Min Act: -0.1700

Data Index: 4065917 (Open Web Text)

Max Activating Token Index: 101

Text #7

Max Range: 2.9301. Min Range: -2.9301

Max Act: 2.8341. Min Act: -0.1700

Data Index: 7102966 (Open Web Text)

Max Activating Token Index: 176

Text #8

Max Range: 2.9301. Min Range: -2.9301

Max Act: 2.8138. Min Act: -0.1700

Data Index: 2621294 (Open Web Text)

Max Activating Token Index: 402

Text #9

Max Range: 2.9301. Min Range: -2.9301

Max Act: 2.7672. Min Act: -0.1700

Data Index: 2791503 (Open Web Text)

Max Activating Token Index: 156

Text #10

Max Range: 2.9301. Min Range: -2.9301

Max Act: 2.7839. Min Act: -0.1700

Data Index: 5454338 (Open Web Text)

Max Activating Token Index: 57

Text #11

Max Range: 2.9301. Min Range: -2.9301

Max Act: 2.7776. Min Act: -0.1700

Data Index: 6364803 (Open Web Text)

Max Activating Token Index: 346

Text #12

Max Range: 2.9301. Min Range: -2.9301

Max Act: 2.7869. Min Act: -0.1700

Data Index: 2408697 (Open Web Text)

Max Activating Token Index: 249

Text #13

Max Range: 2.9301. Min Range: -2.9301

Max Act: 2.7688. Min Act: -0.1700

Data Index: 761192 (Open Web Text)

Max Activating Token Index: 766

Text #14

Max Range: 2.9301. Min Range: -2.9301

Max Act: 2.7634. Min Act: -0.1700

Data Index: 1663035 (Open Web Text)

Max Activating Token Index: 969

Text #15

Max Range: 2.9301. Min Range: -2.9301

Max Act: 2.7698. Min Act: -0.1700

Data Index: 7173972 (Open Web Text)

Max Activating Token Index: 225

Text #16

Max Range: 2.9301. Min Range: -2.9301

Max Act: 2.7860. Min Act: -0.1700

Data Index: 1458643 (Open Web Text)

Max Activating Token Index: 378

Text #17

Max Range: 2.9301. Min Range: -2.9301

Max Act: 2.7733. Min Act: -0.1700

Data Index: 215678 (Open Web Text)

Max Activating Token Index: 745

Text #18

Max Range: 2.9301. Min Range: -2.9301

Max Act: 2.7735. Min Act: -0.1700

Data Index: 2165563 (Open Web Text)

Max Activating Token Index: 628

Text #19

Max Range: 2.9301. Min Range: -2.9301

Max Act: 2.7783. Min Act: -0.1700

Data Index: 7471361 (Open Web Text)

Max Activating Token Index: 3