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

Dataset: Open Web Text

Neuron 3069 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: 3.1624. Min Range: -3.1624

Max Act: 3.1624. Min Act: -0.1700

Data Index: 7682875 (Open Web Text)

Max Activating Token Index: 762

Text #1

Max Range: 3.1624. Min Range: -3.1624

Max Act: 3.1547. Min Act: -0.1700

Data Index: 5712209 (Open Web Text)

Max Activating Token Index: 636

Text #2

Max Range: 3.1624. Min Range: -3.1624

Max Act: 3.1454. Min Act: -0.1700

Data Index: 1850371 (Open Web Text)

Max Activating Token Index: 509

Text #3

Max Range: 3.1624. Min Range: -3.1624

Max Act: 3.1161. Min Act: -0.1700

Data Index: 2180837 (Open Web Text)

Max Activating Token Index: 905

Text #4

Max Range: 3.1624. Min Range: -3.1624

Max Act: 3.1230. Min Act: -0.1700

Data Index: 914382 (Open Web Text)

Max Activating Token Index: 308

Text #5

Max Range: 3.1624. Min Range: -3.1624

Max Act: 3.0995. Min Act: -0.1700

Data Index: 270407 (Open Web Text)

Max Activating Token Index: 202

Text #6

Max Range: 3.1624. Min Range: -3.1624

Max Act: 3.1190. Min Act: -0.1700

Data Index: 1687560 (Open Web Text)

Max Activating Token Index: 593

Text #7

Max Range: 3.1624. Min Range: -3.1624

Max Act: 3.0804. Min Act: -0.1700

Data Index: 6699019 (Open Web Text)

Max Activating Token Index: 407

Text #8

Max Range: 3.1624. Min Range: -3.1624

Max Act: 3.0752. Min Act: -0.1700

Data Index: 7493714 (Open Web Text)

Max Activating Token Index: 704

Text #9

Max Range: 3.1624. Min Range: -3.1624

Max Act: 3.0942. Min Act: -0.1700

Data Index: 4549385 (Open Web Text)

Max Activating Token Index: 378

Text #10

Max Range: 3.1624. Min Range: -3.1624

Max Act: 3.0875. Min Act: -0.1700

Data Index: 7077339 (Open Web Text)

Max Activating Token Index: 76

Text #11

Max Range: 3.1624. Min Range: -3.1624

Max Act: 3.0969. Min Act: -0.1700

Data Index: 2365666 (Open Web Text)

Max Activating Token Index: 155

Text #12

Max Range: 3.1624. Min Range: -3.1624

Max Act: 3.0672. Min Act: -0.1700

Data Index: 1321216 (Open Web Text)

Max Activating Token Index: 371

Text #13

Max Range: 3.1624. Min Range: -3.1624

Max Act: 3.0753. Min Act: -0.1700

Data Index: 3144169 (Open Web Text)

Max Activating Token Index: 401

Text #14

Max Range: 3.1624. Min Range: -3.1624

Max Act: 3.0609. Min Act: -0.1700

Data Index: 3914999 (Open Web Text)

Max Activating Token Index: 520

Text #15

Max Range: 3.1624. Min Range: -3.1624

Max Act: 3.0772. Min Act: -0.1700

Data Index: 7407728 (Open Web Text)

Max Activating Token Index: 869

Text #16

Max Range: 3.1624. Min Range: -3.1624

Max Act: 3.0609. Min Act: -0.1700

Data Index: 4430110 (Open Web Text)

Max Activating Token Index: 887

Text #17

Max Range: 3.1624. Min Range: -3.1624

Max Act: 3.0423. Min Act: -0.1700

Data Index: 5986703 (Open Web Text)

Max Activating Token Index: 404

Text #18

Max Range: 3.1624. Min Range: -3.1624

Max Act: 3.0412. Min Act: -0.1700

Data Index: 61531 (Open Web Text)

Max Activating Token Index: 39

Text #19

Max Range: 3.1624. Min Range: -3.1624

Max Act: 3.0509. Min Act: -0.1700

Data Index: 4772947 (Open Web Text)

Max Activating Token Index: 783