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

Dataset: Open Web Text

Neuron 357 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: 5.0858. Min Range: -5.0858

Max Act: 5.0736. Min Act: -0.1700

Data Index: 1474524 (Open Web Text)

Max Activating Token Index: 558

Text #1

Max Range: 5.0858. Min Range: -5.0858

Max Act: 5.0858. Min Act: -0.1700

Data Index: 2395180 (Open Web Text)

Max Activating Token Index: 485

Text #2

Max Range: 5.0858. Min Range: -5.0858

Max Act: 4.9710. Min Act: -0.1700

Data Index: 1142624 (Open Web Text)

Max Activating Token Index: 136

Text #3

Max Range: 5.0858. Min Range: -5.0858

Max Act: 4.9886. Min Act: -0.1700

Data Index: 5490389 (Open Web Text)

Max Activating Token Index: 562

Text #4

Max Range: 5.0858. Min Range: -5.0858

Max Act: 4.9451. Min Act: -0.1700

Data Index: 5518266 (Open Web Text)

Max Activating Token Index: 734

Text #5

Max Range: 5.0858. Min Range: -5.0858

Max Act: 4.9462. Min Act: -0.1700

Data Index: 7611972 (Open Web Text)

Max Activating Token Index: 270

Text #6

Max Range: 5.0858. Min Range: -5.0858

Max Act: 4.9540. Min Act: -0.1700

Data Index: 7474414 (Open Web Text)

Max Activating Token Index: 313

Text #7

Max Range: 5.0858. Min Range: -5.0858

Max Act: 4.9072. Min Act: -0.1700

Data Index: 5507860 (Open Web Text)

Max Activating Token Index: 838

Text #8

Max Range: 5.0858. Min Range: -5.0858

Max Act: 4.9326. Min Act: -0.1700

Data Index: 7034226 (Open Web Text)

Max Activating Token Index: 341

Text #9

Max Range: 5.0858. Min Range: -5.0858

Max Act: 4.8368. Min Act: -0.1700

Data Index: 1737355 (Open Web Text)

Max Activating Token Index: 609

Text #10

Max Range: 5.0858. Min Range: -5.0858

Max Act: 4.8646. Min Act: -0.1700

Data Index: 5288143 (Open Web Text)

Max Activating Token Index: 475

Text #11

Max Range: 5.0858. Min Range: -5.0858

Max Act: 4.8967. Min Act: -0.1700

Data Index: 1655510 (Open Web Text)

Max Activating Token Index: 645

Text #12

Max Range: 5.0858. Min Range: -5.0858

Max Act: 4.8643. Min Act: -0.1700

Data Index: 5399254 (Open Web Text)

Max Activating Token Index: 368

Text #13

Max Range: 5.0858. Min Range: -5.0858

Max Act: 4.8659. Min Act: -0.1700

Data Index: 5980900 (Open Web Text)

Max Activating Token Index: 317

Text #14

Max Range: 5.0858. Min Range: -5.0858

Max Act: 4.8674. Min Act: -0.1700

Data Index: 2149166 (Open Web Text)

Max Activating Token Index: 706

Text #15

Max Range: 5.0858. Min Range: -5.0858

Max Act: 4.8739. Min Act: -0.1700

Data Index: 61170 (Open Web Text)

Max Activating Token Index: 753

Text #16

Max Range: 5.0858. Min Range: -5.0858

Max Act: 4.8214. Min Act: -0.1700

Data Index: 1079979 (Open Web Text)

Max Activating Token Index: 173

Text #17

Max Range: 5.0858. Min Range: -5.0858

Max Act: 4.8263. Min Act: -0.1700

Data Index: 3942476 (Open Web Text)

Max Activating Token Index: 755

Text #18

Max Range: 5.0858. Min Range: -5.0858

Max Act: 4.8214. Min Act: -0.1700

Data Index: 3729056 (Open Web Text)

Max Activating Token Index: 383

Text #19

Max Range: 5.0858. Min Range: -5.0858

Max Act: 4.8080. Min Act: -0.1700

Data Index: 2852476 (Open Web Text)

Max Activating Token Index: 280