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

Dataset: Open Web Text

Neuron 114 in Layer 6

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: 3.9604. Min Range: -3.9604

Max Act: 3.9604. Min Act: -0.1700

Data Index: 4997707 (Open Web Text)

Max Activating Token Index: 782

Text #1

Max Range: 3.9604. Min Range: -3.9604

Max Act: 3.9037. Min Act: -0.1700

Data Index: 962602 (Open Web Text)

Max Activating Token Index: 545

Text #2

Max Range: 3.9604. Min Range: -3.9604

Max Act: 3.8572. Min Act: -0.1700

Data Index: 1991775 (Open Web Text)

Max Activating Token Index: 489

Text #3

Max Range: 3.9604. Min Range: -3.9604

Max Act: 3.8659. Min Act: -0.1700

Data Index: 3438198 (Open Web Text)

Max Activating Token Index: 798

Text #4

Max Range: 3.9604. Min Range: -3.9604

Max Act: 3.8533. Min Act: -0.1700

Data Index: 2323963 (Open Web Text)

Max Activating Token Index: 238

Text #5

Max Range: 3.9604. Min Range: -3.9604

Max Act: 3.8313. Min Act: -0.1700

Data Index: 1897435 (Open Web Text)

Max Activating Token Index: 969

Text #6

Max Range: 3.9604. Min Range: -3.9604

Max Act: 3.7797. Min Act: -0.1700

Data Index: 2048757 (Open Web Text)

Max Activating Token Index: 732

Text #7

Max Range: 3.9604. Min Range: -3.9604

Max Act: 3.7672. Min Act: -0.1700

Data Index: 7371147 (Open Web Text)

Max Activating Token Index: 327

Text #8

Max Range: 3.9604. Min Range: -3.9604

Max Act: 3.7753. Min Act: -0.1700

Data Index: 3898715 (Open Web Text)

Max Activating Token Index: 336

Text #9

Max Range: 3.9604. Min Range: -3.9604

Max Act: 3.7673. Min Act: -0.1700

Data Index: 3842186 (Open Web Text)

Max Activating Token Index: 222

Text #10

Max Range: 3.9604. Min Range: -3.9604

Max Act: 3.7636. Min Act: -0.1700

Data Index: 349917 (Open Web Text)

Max Activating Token Index: 511

Text #11

Max Range: 3.9604. Min Range: -3.9604

Max Act: 3.7779. Min Act: -0.1700

Data Index: 314831 (Open Web Text)

Max Activating Token Index: 293

Text #12

Max Range: 3.9604. Min Range: -3.9604

Max Act: 3.7695. Min Act: -0.1700

Data Index: 2708848 (Open Web Text)

Max Activating Token Index: 744

Text #13

Max Range: 3.9604. Min Range: -3.9604

Max Act: 3.7286. Min Act: -0.1700

Data Index: 1898562 (Open Web Text)

Max Activating Token Index: 590

Text #14

Max Range: 3.9604. Min Range: -3.9604

Max Act: 3.7080. Min Act: -0.1700

Data Index: 1033930 (Open Web Text)

Max Activating Token Index: 902

Text #15

Max Range: 3.9604. Min Range: -3.9604

Max Act: 3.7285. Min Act: -0.1700

Data Index: 7738099 (Open Web Text)

Max Activating Token Index: 151

Text #16

Max Range: 3.9604. Min Range: -3.9604

Max Act: 3.7317. Min Act: -0.1700

Data Index: 5697868 (Open Web Text)

Max Activating Token Index: 203

Text #17

Max Range: 3.9604. Min Range: -3.9604

Max Act: 3.7009. Min Act: -0.1700

Data Index: 8017152 (Open Web Text)

Max Activating Token Index: 329

Text #18

Max Range: 3.9604. Min Range: -3.9604

Max Act: 3.7067. Min Act: -0.1700

Data Index: 4909005 (Open Web Text)

Max Activating Token Index: 524

Text #19

Max Range: 3.9604. Min Range: -3.9604

Max Act: 3.7111. Min Act: -0.1700

Data Index: 7583328 (Open Web Text)

Max Activating Token Index: 251