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

Dataset: Open Web Text

Neuron 1930 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: 5.0714. Min Range: -5.0714

Max Act: 5.0714. Min Act: -0.1700

Data Index: 8462660 (Open Web Text)

Max Activating Token Index: 957

Text #1

Max Range: 5.0714. Min Range: -5.0714

Max Act: 4.9830. Min Act: -0.1700

Data Index: 8656547 (Open Web Text)

Max Activating Token Index: 435

Text #2

Max Range: 5.0714. Min Range: -5.0714

Max Act: 5.0115. Min Act: -0.1700

Data Index: 3610247 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 5.0714. Min Range: -5.0714

Max Act: 5.0038. Min Act: -0.1700

Data Index: 4078746 (Open Web Text)

Max Activating Token Index: 400

Text #4

Max Range: 5.0714. Min Range: -5.0714

Max Act: 4.9843. Min Act: -0.1700

Data Index: 4666632 (Open Web Text)

Max Activating Token Index: 881

Text #5

Max Range: 5.0714. Min Range: -5.0714

Max Act: 5.0025. Min Act: -0.1700

Data Index: 6550755 (Open Web Text)

Max Activating Token Index: 532

Text #6

Max Range: 5.0714. Min Range: -5.0714

Max Act: 4.9908. Min Act: -0.1700

Data Index: 6554678 (Open Web Text)

Max Activating Token Index: 459

Text #7

Max Range: 5.0714. Min Range: -5.0714

Max Act: 4.9357. Min Act: -0.1700

Data Index: 1884643 (Open Web Text)

Max Activating Token Index: 518

Text #8

Max Range: 5.0714. Min Range: -5.0714

Max Act: 4.9535. Min Act: -0.1700

Data Index: 8517631 (Open Web Text)

Max Activating Token Index: 233

Text #9

Max Range: 5.0714. Min Range: -5.0714

Max Act: 4.9702. Min Act: -0.1700

Data Index: 8044719 (Open Web Text)

Max Activating Token Index: 103

Text #10

Max Range: 5.0714. Min Range: -5.0714

Max Act: 4.9603. Min Act: -0.1700

Data Index: 7650542 (Open Web Text)

Max Activating Token Index: 977

Text #11

Max Range: 5.0714. Min Range: -5.0714

Max Act: 4.9880. Min Act: -0.1700

Data Index: 7478361 (Open Web Text)

Max Activating Token Index: 426

Text #12

Max Range: 5.0714. Min Range: -5.0714

Max Act: 4.9605. Min Act: -0.1700

Data Index: 922844 (Open Web Text)

Max Activating Token Index: 661

Text #13

Max Range: 5.0714. Min Range: -5.0714

Max Act: 4.9447. Min Act: -0.1700

Data Index: 7331847 (Open Web Text)

Max Activating Token Index: 707

Text #14

Max Range: 5.0714. Min Range: -5.0714

Max Act: 4.9553. Min Act: -0.1700

Data Index: 6877878 (Open Web Text)

Max Activating Token Index: 396

Text #15

Max Range: 5.0714. Min Range: -5.0714

Max Act: 4.9802. Min Act: -0.1700

Data Index: 6016589 (Open Web Text)

Max Activating Token Index: 727

Text #16

Max Range: 5.0714. Min Range: -5.0714

Max Act: 4.9416. Min Act: -0.1700

Data Index: 110556 (Open Web Text)

Max Activating Token Index: 429

Text #17

Max Range: 5.0714. Min Range: -5.0714

Max Act: 4.9814. Min Act: -0.1700

Data Index: 5422870 (Open Web Text)

Max Activating Token Index: 446

Text #18

Max Range: 5.0714. Min Range: -5.0714

Max Act: 4.9682. Min Act: -0.1700

Data Index: 5141695 (Open Web Text)

Max Activating Token Index: 373

Text #19

Max Range: 5.0714. Min Range: -5.0714

Max Act: 4.9661. Min Act: -0.1700

Data Index: 416536 (Open Web Text)

Max Activating Token Index: 761