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

Dataset: Open Web Text

Neuron 1781 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: 4.1273. Min Range: -4.1273

Max Act: 4.1273. Min Act: -0.1700

Data Index: 2425231 (Open Web Text)

Max Activating Token Index: 630

Text #1

Max Range: 4.1273. Min Range: -4.1273

Max Act: 3.9512. Min Act: -0.1700

Data Index: 2131814 (Open Web Text)

Max Activating Token Index: 437

Text #2

Max Range: 4.1273. Min Range: -4.1273

Max Act: 3.9404. Min Act: -0.1700

Data Index: 4588748 (Open Web Text)

Max Activating Token Index: 480

Text #3

Max Range: 4.1273. Min Range: -4.1273

Max Act: 3.9439. Min Act: -0.1700

Data Index: 5291157 (Open Web Text)

Max Activating Token Index: 632

Text #4

Max Range: 4.1273. Min Range: -4.1273

Max Act: 3.9341. Min Act: -0.1700

Data Index: 1822159 (Open Web Text)

Max Activating Token Index: 859

Text #5

Max Range: 4.1273. Min Range: -4.1273

Max Act: 3.9128. Min Act: -0.1700

Data Index: 2741017 (Open Web Text)

Max Activating Token Index: 474

Text #6

Max Range: 4.1273. Min Range: -4.1273

Max Act: 3.8649. Min Act: -0.1700

Data Index: 4972225 (Open Web Text)

Max Activating Token Index: 287

Text #7

Max Range: 4.1273. Min Range: -4.1273

Max Act: 3.8723. Min Act: -0.1700

Data Index: 8737432 (Open Web Text)

Max Activating Token Index: 837

Text #8

Max Range: 4.1273. Min Range: -4.1273

Max Act: 3.8695. Min Act: -0.1700

Data Index: 2039503 (Open Web Text)

Max Activating Token Index: 149

Text #9

Max Range: 4.1273. Min Range: -4.1273

Max Act: 3.8610. Min Act: -0.1700

Data Index: 3059093 (Open Web Text)

Max Activating Token Index: 249

Text #10

Max Range: 4.1273. Min Range: -4.1273

Max Act: 3.8853. Min Act: -0.1700

Data Index: 4046420 (Open Web Text)

Max Activating Token Index: 412

Text #11

Max Range: 4.1273. Min Range: -4.1273

Max Act: 3.8759. Min Act: -0.1700

Data Index: 286657 (Open Web Text)

Max Activating Token Index: 493

Text #12

Max Range: 4.1273. Min Range: -4.1273

Max Act: 3.8665. Min Act: -0.1700

Data Index: 1921680 (Open Web Text)

Max Activating Token Index: 640

Text #13

Max Range: 4.1273. Min Range: -4.1273

Max Act: 3.8598. Min Act: -0.1700

Data Index: 814890 (Open Web Text)

Max Activating Token Index: 97

Text #14

Max Range: 4.1273. Min Range: -4.1273

Max Act: 3.8726. Min Act: -0.1700

Data Index: 6840146 (Open Web Text)

Max Activating Token Index: 707

Text #15

Max Range: 4.1273. Min Range: -4.1273

Max Act: 3.8340. Min Act: -0.1700

Data Index: 8516386 (Open Web Text)

Max Activating Token Index: 578

Text #16

Max Range: 4.1273. Min Range: -4.1273

Max Act: 3.7869. Min Act: -0.1700

Data Index: 1102757 (Open Web Text)

Max Activating Token Index: 739

Text #17

Max Range: 4.1273. Min Range: -4.1273

Max Act: 3.8175. Min Act: -0.1700

Data Index: 6048879 (Open Web Text)

Max Activating Token Index: 145

Text #18

Max Range: 4.1273. Min Range: -4.1273

Max Act: 3.8280. Min Act: -0.1700

Data Index: 7777672 (Open Web Text)

Max Activating Token Index: 122

Text #19

Max Range: 4.1273. Min Range: -4.1273

Max Act: 3.8312. Min Act: -0.1700

Data Index: 8221524 (Open Web Text)

Max Activating Token Index: 724