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

Dataset: Open Web Text

Neuron 57 in Layer 0

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: 3.1775. Min Range: -3.1775

Max Act: 3.1775. Min Act: -0.1700

Data Index: 194610 (Open Web Text)

Max Activating Token Index: 878

Text #1

Max Range: 3.1775. Min Range: -3.1775

Max Act: 3.1192. Min Act: -0.1700

Data Index: 6178774 (Open Web Text)

Max Activating Token Index: 880

Text #2

Max Range: 3.1775. Min Range: -3.1775

Max Act: 3.0749. Min Act: -0.1700

Data Index: 2542990 (Open Web Text)

Max Activating Token Index: 812

Text #3

Max Range: 3.1775. Min Range: -3.1775

Max Act: 3.0693. Min Act: -0.1700

Data Index: 8743559 (Open Web Text)

Max Activating Token Index: 696

Text #4

Max Range: 3.1775. Min Range: -3.1775

Max Act: 3.0760. Min Act: -0.1700

Data Index: 5401393 (Open Web Text)

Max Activating Token Index: 213

Text #5

Max Range: 3.1775. Min Range: -3.1775

Max Act: 3.0715. Min Act: -0.1700

Data Index: 8550158 (Open Web Text)

Max Activating Token Index: 318

Text #6

Max Range: 3.1775. Min Range: -3.1775

Max Act: 3.0683. Min Act: -0.1700

Data Index: 1646522 (Open Web Text)

Max Activating Token Index: 231

Text #7

Max Range: 3.1775. Min Range: -3.1775

Max Act: 3.0562. Min Act: -0.1700

Data Index: 8336741 (Open Web Text)

Max Activating Token Index: 225

Text #8

Max Range: 3.1775. Min Range: -3.1775

Max Act: 3.0513. Min Act: -0.1700

Data Index: 7751373 (Open Web Text)

Max Activating Token Index: 664

Text #9

Max Range: 3.1775. Min Range: -3.1775

Max Act: 3.0541. Min Act: -0.1700

Data Index: 4006312 (Open Web Text)

Max Activating Token Index: 356

Text #10

Max Range: 3.1775. Min Range: -3.1775

Max Act: 3.0309. Min Act: -0.1700

Data Index: 7592895 (Open Web Text)

Max Activating Token Index: 600

Text #11

Max Range: 3.1775. Min Range: -3.1775

Max Act: 3.0301. Min Act: -0.1700

Data Index: 6401438 (Open Web Text)

Max Activating Token Index: 636

Text #12

Max Range: 3.1775. Min Range: -3.1775

Max Act: 3.0204. Min Act: -0.1700

Data Index: 5944555 (Open Web Text)

Max Activating Token Index: 916

Text #13

Max Range: 3.1775. Min Range: -3.1775

Max Act: 3.0240. Min Act: -0.1700

Data Index: 5084726 (Open Web Text)

Max Activating Token Index: 852

Text #14

Max Range: 3.1775. Min Range: -3.1775

Max Act: 3.0216. Min Act: -0.1700

Data Index: 4997118 (Open Web Text)

Max Activating Token Index: 928

Text #15

Max Range: 3.1775. Min Range: -3.1775

Max Act: 3.0322. Min Act: -0.1700

Data Index: 7875679 (Open Web Text)

Max Activating Token Index: 283

Text #16

Max Range: 3.1775. Min Range: -3.1775

Max Act: 3.0404. Min Act: -0.1700

Data Index: 2040948 (Open Web Text)

Max Activating Token Index: 1008

Text #17

Max Range: 3.1775. Min Range: -3.1775

Max Act: 3.0326. Min Act: -0.1700

Data Index: 4498810 (Open Web Text)

Max Activating Token Index: 716

Text #18

Max Range: 3.1775. Min Range: -3.1775

Max Act: 3.0206. Min Act: -0.1700

Data Index: 6579191 (Open Web Text)

Max Activating Token Index: 850

Text #19

Max Range: 3.1775. Min Range: -3.1775

Max Act: 3.0100. Min Act: -0.1700

Data Index: 7507796 (Open Web Text)

Max Activating Token Index: 96