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

Dataset: Open Web Text

Neuron 1471 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: 4.1771. Min Range: -4.1771

Max Act: 4.1771. Min Act: -0.1700

Data Index: 1990029 (Open Web Text)

Max Activating Token Index: 266

Text #1

Max Range: 4.1771. Min Range: -4.1771

Max Act: 4.0397. Min Act: -0.1700

Data Index: 2932311 (Open Web Text)

Max Activating Token Index: 735

Text #2

Max Range: 4.1771. Min Range: -4.1771

Max Act: 3.9984. Min Act: -0.1700

Data Index: 268648 (Open Web Text)

Max Activating Token Index: 706

Text #3

Max Range: 4.1771. Min Range: -4.1771

Max Act: 3.9841. Min Act: -0.1700

Data Index: 732684 (Open Web Text)

Max Activating Token Index: 896

Text #4

Max Range: 4.1771. Min Range: -4.1771

Max Act: 4.0159. Min Act: -0.1700

Data Index: 4186080 (Open Web Text)

Max Activating Token Index: 37

Text #5

Max Range: 4.1771. Min Range: -4.1771

Max Act: 3.9906. Min Act: -0.1700

Data Index: 7171195 (Open Web Text)

Max Activating Token Index: 908

Text #6

Max Range: 4.1771. Min Range: -4.1771

Max Act: 4.0173. Min Act: -0.1700

Data Index: 3035656 (Open Web Text)

Max Activating Token Index: 854

Text #7

Max Range: 4.1771. Min Range: -4.1771

Max Act: 3.9899. Min Act: -0.1700

Data Index: 6765683 (Open Web Text)

Max Activating Token Index: 635

Text #8

Max Range: 4.1771. Min Range: -4.1771

Max Act: 3.9676. Min Act: -0.1700

Data Index: 1370732 (Open Web Text)

Max Activating Token Index: 569

Text #9

Max Range: 4.1771. Min Range: -4.1771

Max Act: 3.9765. Min Act: -0.1700

Data Index: 88873 (Open Web Text)

Max Activating Token Index: 214

Text #10

Max Range: 4.1771. Min Range: -4.1771

Max Act: 3.9821. Min Act: -0.1700

Data Index: 1052109 (Open Web Text)

Max Activating Token Index: 447

Text #11

Max Range: 4.1771. Min Range: -4.1771

Max Act: 3.9659. Min Act: -0.1700

Data Index: 937077 (Open Web Text)

Max Activating Token Index: 975

Text #12

Max Range: 4.1771. Min Range: -4.1771

Max Act: 3.9663. Min Act: -0.1700

Data Index: 6498007 (Open Web Text)

Max Activating Token Index: 890

Text #13

Max Range: 4.1771. Min Range: -4.1771

Max Act: 3.9825. Min Act: -0.1700

Data Index: 976666 (Open Web Text)

Max Activating Token Index: 685

Text #14

Max Range: 4.1771. Min Range: -4.1771

Max Act: 3.9743. Min Act: -0.1700

Data Index: 4856360 (Open Web Text)

Max Activating Token Index: 196

Text #15

Max Range: 4.1771. Min Range: -4.1771

Max Act: 3.9689. Min Act: -0.1700

Data Index: 4941127 (Open Web Text)

Max Activating Token Index: 989

Text #16

Max Range: 4.1771. Min Range: -4.1771

Max Act: 3.9708. Min Act: -0.1700

Data Index: 937082 (Open Web Text)

Max Activating Token Index: 968

Text #17

Max Range: 4.1771. Min Range: -4.1771

Max Act: 3.9775. Min Act: -0.1700

Data Index: 3034331 (Open Web Text)

Max Activating Token Index: 700

Text #18

Max Range: 4.1771. Min Range: -4.1771

Max Act: 3.9501. Min Act: -0.1700

Data Index: 937079 (Open Web Text)

Max Activating Token Index: 602

Text #19

Max Range: 4.1771. Min Range: -4.1771

Max Act: 3.9264. Min Act: -0.1700

Data Index: 937078 (Open Web Text)

Max Activating Token Index: 107