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

Dataset: Open Web Text

Neuron 666 in Layer 4

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: 3.1599. Min Range: -3.1599

Max Act: 3.1599. Min Act: -0.1700

Data Index: 7864787 (Open Web Text)

Max Activating Token Index: 74

Text #1

Max Range: 3.1599. Min Range: -3.1599

Max Act: 3.0583. Min Act: -0.1700

Data Index: 6458713 (Open Web Text)

Max Activating Token Index: 170

Text #2

Max Range: 3.1599. Min Range: -3.1599

Max Act: 3.0062. Min Act: -0.1700

Data Index: 2292622 (Open Web Text)

Max Activating Token Index: 900

Text #3

Max Range: 3.1599. Min Range: -3.1599

Max Act: 2.9875. Min Act: -0.1700

Data Index: 5217421 (Open Web Text)

Max Activating Token Index: 220

Text #4

Max Range: 3.1599. Min Range: -3.1599

Max Act: 2.9878. Min Act: -0.1700

Data Index: 381030 (Open Web Text)

Max Activating Token Index: 242

Text #5

Max Range: 3.1599. Min Range: -3.1599

Max Act: 3.0063. Min Act: -0.1700

Data Index: 6385401 (Open Web Text)

Max Activating Token Index: 1012

Text #6

Max Range: 3.1599. Min Range: -3.1599

Max Act: 2.9668. Min Act: -0.1700

Data Index: 4332473 (Open Web Text)

Max Activating Token Index: 271

Text #7

Max Range: 3.1599. Min Range: -3.1599

Max Act: 2.9526. Min Act: -0.1700

Data Index: 1580204 (Open Web Text)

Max Activating Token Index: 726

Text #8

Max Range: 3.1599. Min Range: -3.1599

Max Act: 2.9701. Min Act: -0.1700

Data Index: 6780995 (Open Web Text)

Max Activating Token Index: 355

Text #9

Max Range: 3.1599. Min Range: -3.1599

Max Act: 2.9633. Min Act: -0.1700

Data Index: 2292625 (Open Web Text)

Max Activating Token Index: 310

Text #10

Max Range: 3.1599. Min Range: -3.1599

Max Act: 2.9859. Min Act: -0.1700

Data Index: 6024186 (Open Web Text)

Max Activating Token Index: 460

Text #11

Max Range: 3.1599. Min Range: -3.1599

Max Act: 2.9385. Min Act: -0.1700

Data Index: 5799353 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 3.1599. Min Range: -3.1599

Max Act: 2.9372. Min Act: -0.1700

Data Index: 7918112 (Open Web Text)

Max Activating Token Index: 503

Text #13

Max Range: 3.1599. Min Range: -3.1599

Max Act: 2.9355. Min Act: -0.1700

Data Index: 3083811 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 3.1599. Min Range: -3.1599

Max Act: 2.9421. Min Act: -0.1700

Data Index: 6641698 (Open Web Text)

Max Activating Token Index: 612

Text #15

Max Range: 3.1599. Min Range: -3.1599

Max Act: 2.9012. Min Act: -0.1700

Data Index: 6651156 (Open Web Text)

Max Activating Token Index: 972

Text #16

Max Range: 3.1599. Min Range: -3.1599

Max Act: 2.9132. Min Act: -0.1700

Data Index: 3873312 (Open Web Text)

Max Activating Token Index: 788

Text #17

Max Range: 3.1599. Min Range: -3.1599

Max Act: 2.9104. Min Act: -0.1700

Data Index: 8350384 (Open Web Text)

Max Activating Token Index: 182

Text #18

Max Range: 3.1599. Min Range: -3.1599

Max Act: 2.8973. Min Act: -0.1700

Data Index: 4933201 (Open Web Text)

Max Activating Token Index: 669

Text #19

Max Range: 3.1599. Min Range: -3.1599

Max Act: 2.8867. Min Act: -0.1700

Data Index: 2943673 (Open Web Text)

Max Activating Token Index: 933