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

Dataset: Open Web Text

Neuron 595 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: 1.9343. Min Range: -1.9343

Max Act: 1.9343. Min Act: -0.1697

Data Index: 3550572 (Open Web Text)

Max Activating Token Index: 615

Text #1

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.8417. Min Act: -0.1694

Data Index: 5622550 (Open Web Text)

Max Activating Token Index: 608

Text #2

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.8500. Min Act: -0.1700

Data Index: 4509411 (Open Web Text)

Max Activating Token Index: 502

Text #3

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.8353. Min Act: -0.1697

Data Index: 1362067 (Open Web Text)

Max Activating Token Index: 549

Text #4

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.8322. Min Act: -0.1700

Data Index: 7764798 (Open Web Text)

Max Activating Token Index: 623

Text #5

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.8153. Min Act: -0.1700

Data Index: 1499440 (Open Web Text)

Max Activating Token Index: 859

Text #6

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.8131. Min Act: -0.1700

Data Index: 3280697 (Open Web Text)

Max Activating Token Index: 37

Text #7

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.8128. Min Act: -0.1700

Data Index: 422177 (Open Web Text)

Max Activating Token Index: 951

Text #8

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.8322. Min Act: -0.1697

Data Index: 3212909 (Open Web Text)

Max Activating Token Index: 678

Text #9

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.8068. Min Act: -0.1700

Data Index: 4191597 (Open Web Text)

Max Activating Token Index: 693

Text #10

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.7905. Min Act: -0.1700

Data Index: 7501071 (Open Web Text)

Max Activating Token Index: 624

Text #11

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.7839. Min Act: -0.1699

Data Index: 2086014 (Open Web Text)

Max Activating Token Index: 605

Text #12

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.8054. Min Act: -0.1647

Data Index: 4745493 (Open Web Text)

Max Activating Token Index: 644

Text #13

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.7938. Min Act: -0.1700

Data Index: 6206654 (Open Web Text)

Max Activating Token Index: 643

Text #14

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.7927. Min Act: -0.1700

Data Index: 1989151 (Open Web Text)

Max Activating Token Index: 1001

Text #15

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.7870. Min Act: -0.1699

Data Index: 1572098 (Open Web Text)

Max Activating Token Index: 613

Text #16

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.7892. Min Act: -0.1700

Data Index: 3870030 (Open Web Text)

Max Activating Token Index: 487

Text #17

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.7799. Min Act: -0.1700

Data Index: 3896845 (Open Web Text)

Max Activating Token Index: 647

Text #18

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.7822. Min Act: -0.1700

Data Index: 1511210 (Open Web Text)

Max Activating Token Index: 633

Text #19

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.7739. Min Act: -0.1700

Data Index: 2515825 (Open Web Text)

Max Activating Token Index: 567