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

Dataset: Open Web Text

Neuron 647 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: 4.0090. Min Range: -4.0090

Max Act: 4.0090. Min Act: -0.1700

Data Index: 7898667 (Open Web Text)

Max Activating Token Index: 982

Text #1

Max Range: 4.0090. Min Range: -4.0090

Max Act: 3.9685. Min Act: -0.1700

Data Index: 2078215 (Open Web Text)

Max Activating Token Index: 610

Text #2

Max Range: 4.0090. Min Range: -4.0090

Max Act: 3.9014. Min Act: -0.1700

Data Index: 4712974 (Open Web Text)

Max Activating Token Index: 652

Text #3

Max Range: 4.0090. Min Range: -4.0090

Max Act: 3.8924. Min Act: -0.1700

Data Index: 7375531 (Open Web Text)

Max Activating Token Index: 1003

Text #4

Max Range: 4.0090. Min Range: -4.0090

Max Act: 3.8837. Min Act: -0.1700

Data Index: 8739565 (Open Web Text)

Max Activating Token Index: 949

Text #5

Max Range: 4.0090. Min Range: -4.0090

Max Act: 3.8813. Min Act: -0.1700

Data Index: 8090910 (Open Web Text)

Max Activating Token Index: 996

Text #6

Max Range: 4.0090. Min Range: -4.0090

Max Act: 3.8591. Min Act: -0.1700

Data Index: 3905389 (Open Web Text)

Max Activating Token Index: 605

Text #7

Max Range: 4.0090. Min Range: -4.0090

Max Act: 3.8633. Min Act: -0.1700

Data Index: 7304170 (Open Web Text)

Max Activating Token Index: 109

Text #8

Max Range: 4.0090. Min Range: -4.0090

Max Act: 3.8618. Min Act: -0.1700

Data Index: 1764405 (Open Web Text)

Max Activating Token Index: 883

Text #9

Max Range: 4.0090. Min Range: -4.0090

Max Act: 3.8429. Min Act: -0.1700

Data Index: 8638305 (Open Web Text)

Max Activating Token Index: 207

Text #10

Max Range: 4.0090. Min Range: -4.0090

Max Act: 3.8017. Min Act: -0.1700

Data Index: 1963952 (Open Web Text)

Max Activating Token Index: 513

Text #11

Max Range: 4.0090. Min Range: -4.0090

Max Act: 3.7584. Min Act: -0.1700

Data Index: 76541 (Open Web Text)

Max Activating Token Index: 323

Text #12

Max Range: 4.0090. Min Range: -4.0090

Max Act: 3.7924. Min Act: -0.1700

Data Index: 1207315 (Open Web Text)

Max Activating Token Index: 216

Text #13

Max Range: 4.0090. Min Range: -4.0090

Max Act: 3.7858. Min Act: -0.1700

Data Index: 5565835 (Open Web Text)

Max Activating Token Index: 553

Text #14

Max Range: 4.0090. Min Range: -4.0090

Max Act: 3.7650. Min Act: -0.1700

Data Index: 3682479 (Open Web Text)

Max Activating Token Index: 268

Text #15

Max Range: 4.0090. Min Range: -4.0090

Max Act: 3.7641. Min Act: -0.1700

Data Index: 5205223 (Open Web Text)

Max Activating Token Index: 522

Text #16

Max Range: 4.0090. Min Range: -4.0090

Max Act: 3.7963. Min Act: -0.1700

Data Index: 5059529 (Open Web Text)

Max Activating Token Index: 719

Text #17

Max Range: 4.0090. Min Range: -4.0090

Max Act: 3.7639. Min Act: -0.1700

Data Index: 3959676 (Open Web Text)

Max Activating Token Index: 368

Text #18

Max Range: 4.0090. Min Range: -4.0090

Max Act: 3.7898. Min Act: -0.1700

Data Index: 8150139 (Open Web Text)

Max Activating Token Index: 668

Text #19

Max Range: 4.0090. Min Range: -4.0090

Max Act: 3.7774. Min Act: -0.1700

Data Index: 2412187 (Open Web Text)

Max Activating Token Index: 223