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

Dataset: Open Web Text

Neuron 2015 in Layer 3

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: 3.6631. Min Range: -3.6631

Max Act: 3.6631. Min Act: -0.1700

Data Index: 2506845 (Open Web Text)

Max Activating Token Index: 468

Text #1

Max Range: 3.6631. Min Range: -3.6631

Max Act: 3.6293. Min Act: -0.1700

Data Index: 5440087 (Open Web Text)

Max Activating Token Index: 431

Text #2

Max Range: 3.6631. Min Range: -3.6631

Max Act: 3.5897. Min Act: -0.1700

Data Index: 6805443 (Open Web Text)

Max Activating Token Index: 454

Text #3

Max Range: 3.6631. Min Range: -3.6631

Max Act: 3.5700. Min Act: -0.1700

Data Index: 3646736 (Open Web Text)

Max Activating Token Index: 948

Text #4

Max Range: 3.6631. Min Range: -3.6631

Max Act: 3.5799. Min Act: -0.1700

Data Index: 5458936 (Open Web Text)

Max Activating Token Index: 411

Text #5

Max Range: 3.6631. Min Range: -3.6631

Max Act: 3.5762. Min Act: -0.1700

Data Index: 1241374 (Open Web Text)

Max Activating Token Index: 256

Text #6

Max Range: 3.6631. Min Range: -3.6631

Max Act: 3.5615. Min Act: -0.1700

Data Index: 2113212 (Open Web Text)

Max Activating Token Index: 856

Text #7

Max Range: 3.6631. Min Range: -3.6631

Max Act: 3.5630. Min Act: -0.1700

Data Index: 6601732 (Open Web Text)

Max Activating Token Index: 962

Text #8

Max Range: 3.6631. Min Range: -3.6631

Max Act: 3.5790. Min Act: -0.1700

Data Index: 4387596 (Open Web Text)

Max Activating Token Index: 714

Text #9

Max Range: 3.6631. Min Range: -3.6631

Max Act: 3.5687. Min Act: -0.1700

Data Index: 5865763 (Open Web Text)

Max Activating Token Index: 424

Text #10

Max Range: 3.6631. Min Range: -3.6631

Max Act: 3.5527. Min Act: -0.1700

Data Index: 1772951 (Open Web Text)

Max Activating Token Index: 852

Text #11

Max Range: 3.6631. Min Range: -3.6631

Max Act: 3.5406. Min Act: -0.1700

Data Index: 149984 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 3.6631. Min Range: -3.6631

Max Act: 3.5497. Min Act: -0.1700

Data Index: 7086256 (Open Web Text)

Max Activating Token Index: 255

Text #13

Max Range: 3.6631. Min Range: -3.6631

Max Act: 3.5351. Min Act: -0.1700

Data Index: 6475169 (Open Web Text)

Max Activating Token Index: 298

Text #14

Max Range: 3.6631. Min Range: -3.6631

Max Act: 3.5543. Min Act: -0.1700

Data Index: 814721 (Open Web Text)

Max Activating Token Index: 847

Text #15

Max Range: 3.6631. Min Range: -3.6631

Max Act: 3.5013. Min Act: -0.1700

Data Index: 1899537 (Open Web Text)

Max Activating Token Index: 728

Text #16

Max Range: 3.6631. Min Range: -3.6631

Max Act: 3.5136. Min Act: -0.1700

Data Index: 60815 (Open Web Text)

Max Activating Token Index: 420

Text #17

Max Range: 3.6631. Min Range: -3.6631

Max Act: 3.5190. Min Act: -0.1700

Data Index: 2991684 (Open Web Text)

Max Activating Token Index: 880

Text #18

Max Range: 3.6631. Min Range: -3.6631

Max Act: 3.5174. Min Act: -0.1700

Data Index: 2783859 (Open Web Text)

Max Activating Token Index: 570

Text #19

Max Range: 3.6631. Min Range: -3.6631

Max Act: 3.5285. Min Act: -0.1700

Data Index: 1844545 (Open Web Text)

Max Activating Token Index: 98