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

Dataset: Open Web Text

Neuron 1255 in Layer 2

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: 1.7368. Min Range: -1.7368

Max Act: 1.7368. Min Act: -0.1700

Data Index: 3416864 (Open Web Text)

Max Activating Token Index: 213

Text #1

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.6375. Min Act: -0.1700

Data Index: 4634655 (Open Web Text)

Max Activating Token Index: 254

Text #2

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.6240. Min Act: -0.1646

Data Index: 1615901 (Open Web Text)

Max Activating Token Index: 997

Text #3

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.6065. Min Act: -0.1700

Data Index: 3589714 (Open Web Text)

Max Activating Token Index: 687

Text #4

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.6243. Min Act: -0.1693

Data Index: 3846289 (Open Web Text)

Max Activating Token Index: 432

Text #5

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.5751. Min Act: -0.1689

Data Index: 3951162 (Open Web Text)

Max Activating Token Index: 102

Text #6

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.5708. Min Act: -0.1691

Data Index: 6851864 (Open Web Text)

Max Activating Token Index: 912

Text #7

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.5542. Min Act: -0.1687

Data Index: 7133428 (Open Web Text)

Max Activating Token Index: 963

Text #8

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.5554. Min Act: -0.1700

Data Index: 7144271 (Open Web Text)

Max Activating Token Index: 199

Text #9

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.5770. Min Act: -0.1700

Data Index: 5949670 (Open Web Text)

Max Activating Token Index: 596

Text #10

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.5670. Min Act: -0.1700

Data Index: 4469189 (Open Web Text)

Max Activating Token Index: 269

Text #11

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.5388. Min Act: -0.1619

Data Index: 7356842 (Open Web Text)

Max Activating Token Index: 614

Text #12

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.5528. Min Act: -0.1674

Data Index: 801151 (Open Web Text)

Max Activating Token Index: 895

Text #13

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.5523. Min Act: -0.1683

Data Index: 1039514 (Open Web Text)

Max Activating Token Index: 229

Text #14

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.5442. Min Act: -0.1690

Data Index: 1776488 (Open Web Text)

Max Activating Token Index: 706

Text #15

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.5426. Min Act: -0.1698

Data Index: 4531074 (Open Web Text)

Max Activating Token Index: 377

Text #16

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.5546. Min Act: -0.1700

Data Index: 3336356 (Open Web Text)

Max Activating Token Index: 786

Text #17

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.5544. Min Act: -0.1700

Data Index: 3259728 (Open Web Text)

Max Activating Token Index: 203

Text #18

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.5506. Min Act: -0.1664

Data Index: 3529541 (Open Web Text)

Max Activating Token Index: 860

Text #19

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.5551. Min Act: -0.1700

Data Index: 7052638 (Open Web Text)

Max Activating Token Index: 485