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

Dataset: Open Web Text

Neuron 841 in Layer 5

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: 4.0662. Min Range: -4.0662

Max Act: 4.0662. Min Act: -0.1700

Data Index: 8201235 (Open Web Text)

Max Activating Token Index: 906

Text #1

Max Range: 4.0662. Min Range: -4.0662

Max Act: 4.0141. Min Act: -0.1700

Data Index: 822420 (Open Web Text)

Max Activating Token Index: 566

Text #2

Max Range: 4.0662. Min Range: -4.0662

Max Act: 4.0122. Min Act: -0.1700

Data Index: 640000 (Open Web Text)

Max Activating Token Index: 877

Text #3

Max Range: 4.0662. Min Range: -4.0662

Max Act: 3.9855. Min Act: -0.1700

Data Index: 7102603 (Open Web Text)

Max Activating Token Index: 977

Text #4

Max Range: 4.0662. Min Range: -4.0662

Max Act: 3.9282. Min Act: -0.1700

Data Index: 3476454 (Open Web Text)

Max Activating Token Index: 406

Text #5

Max Range: 4.0662. Min Range: -4.0662

Max Act: 3.9645. Min Act: -0.1700

Data Index: 821097 (Open Web Text)

Max Activating Token Index: 760

Text #6

Max Range: 4.0662. Min Range: -4.0662

Max Act: 3.9544. Min Act: -0.1700

Data Index: 3137877 (Open Web Text)

Max Activating Token Index: 932

Text #7

Max Range: 4.0662. Min Range: -4.0662

Max Act: 3.9269. Min Act: -0.1700

Data Index: 3558217 (Open Web Text)

Max Activating Token Index: 912

Text #8

Max Range: 4.0662. Min Range: -4.0662

Max Act: 3.9060. Min Act: -0.1700

Data Index: 8191837 (Open Web Text)

Max Activating Token Index: 878

Text #9

Max Range: 4.0662. Min Range: -4.0662

Max Act: 3.8677. Min Act: -0.1700

Data Index: 8745842 (Open Web Text)

Max Activating Token Index: 897

Text #10

Max Range: 4.0662. Min Range: -4.0662

Max Act: 3.8626. Min Act: -0.1700

Data Index: 5213598 (Open Web Text)

Max Activating Token Index: 731

Text #11

Max Range: 4.0662. Min Range: -4.0662

Max Act: 3.8876. Min Act: -0.1700

Data Index: 4147850 (Open Web Text)

Max Activating Token Index: 158

Text #12

Max Range: 4.0662. Min Range: -4.0662

Max Act: 3.9039. Min Act: -0.1700

Data Index: 4927424 (Open Web Text)

Max Activating Token Index: 805

Text #13

Max Range: 4.0662. Min Range: -4.0662

Max Act: 3.8803. Min Act: -0.1700

Data Index: 8725967 (Open Web Text)

Max Activating Token Index: 102

Text #14

Max Range: 4.0662. Min Range: -4.0662

Max Act: 3.8744. Min Act: -0.1700

Data Index: 2071237 (Open Web Text)

Max Activating Token Index: 468

Text #15

Max Range: 4.0662. Min Range: -4.0662

Max Act: 3.8806. Min Act: -0.1700

Data Index: 151432 (Open Web Text)

Max Activating Token Index: 817

Text #16

Max Range: 4.0662. Min Range: -4.0662

Max Act: 3.8684. Min Act: -0.1700

Data Index: 7681155 (Open Web Text)

Max Activating Token Index: 257

Text #17

Max Range: 4.0662. Min Range: -4.0662

Max Act: 3.8864. Min Act: -0.1700

Data Index: 5615316 (Open Web Text)

Max Activating Token Index: 1000

Text #18

Max Range: 4.0662. Min Range: -4.0662

Max Act: 3.8770. Min Act: -0.1700

Data Index: 7494319 (Open Web Text)

Max Activating Token Index: 296

Text #19

Max Range: 4.0662. Min Range: -4.0662

Max Act: 3.8449. Min Act: -0.1700

Data Index: 4322098 (Open Web Text)

Max Activating Token Index: 831