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

Dataset: Open Web Text

Neuron 72 in Layer 3

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: 1.9713. Min Range: -1.9713

Max Act: 1.9566. Min Act: -0.1700

Data Index: 6753377 (Open Web Text)

Max Activating Token Index: 832

Text #1

Max Range: 1.9713. Min Range: -1.9713

Max Act: 1.9698. Min Act: -0.1700

Data Index: 5687077 (Open Web Text)

Max Activating Token Index: 102

Text #2

Max Range: 1.9713. Min Range: -1.9713

Max Act: 1.9661. Min Act: -0.1700

Data Index: 6878770 (Open Web Text)

Max Activating Token Index: 852

Text #3

Max Range: 1.9713. Min Range: -1.9713

Max Act: 1.9713. Min Act: -0.1700

Data Index: 3029118 (Open Web Text)

Max Activating Token Index: 940

Text #4

Max Range: 1.9713. Min Range: -1.9713

Max Act: 1.9637. Min Act: -0.1700

Data Index: 1295773 (Open Web Text)

Max Activating Token Index: 522

Text #5

Max Range: 1.9713. Min Range: -1.9713

Max Act: 1.9614. Min Act: -0.1700

Data Index: 2797521 (Open Web Text)

Max Activating Token Index: 817

Text #6

Max Range: 1.9713. Min Range: -1.9713

Max Act: 1.9395. Min Act: -0.1700

Data Index: 6656302 (Open Web Text)

Max Activating Token Index: 780

Text #7

Max Range: 1.9713. Min Range: -1.9713

Max Act: 1.9400. Min Act: -0.1700

Data Index: 98505 (Open Web Text)

Max Activating Token Index: 551

Text #8

Max Range: 1.9713. Min Range: -1.9713

Max Act: 1.9309. Min Act: -0.1700

Data Index: 4819736 (Open Web Text)

Max Activating Token Index: 141

Text #9

Max Range: 1.9713. Min Range: -1.9713

Max Act: 1.9305. Min Act: -0.1700

Data Index: 7893737 (Open Web Text)

Max Activating Token Index: 763

Text #10

Max Range: 1.9713. Min Range: -1.9713

Max Act: 1.9408. Min Act: -0.1700

Data Index: 3211852 (Open Web Text)

Max Activating Token Index: 399

Text #11

Max Range: 1.9713. Min Range: -1.9713

Max Act: 1.9508. Min Act: -0.1700

Data Index: 5751941 (Open Web Text)

Max Activating Token Index: 774

Text #12

Max Range: 1.9713. Min Range: -1.9713

Max Act: 1.9400. Min Act: -0.1700

Data Index: 563158 (Open Web Text)

Max Activating Token Index: 535

Text #13

Max Range: 1.9713. Min Range: -1.9713

Max Act: 1.9125. Min Act: -0.1700

Data Index: 5316974 (Open Web Text)

Max Activating Token Index: 872

Text #14

Max Range: 1.9713. Min Range: -1.9713

Max Act: 1.9227. Min Act: -0.1700

Data Index: 3370967 (Open Web Text)

Max Activating Token Index: 988

Text #15

Max Range: 1.9713. Min Range: -1.9713

Max Act: 1.9035. Min Act: -0.1700

Data Index: 4601849 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 1.9713. Min Range: -1.9713

Max Act: 1.9063. Min Act: -0.1700

Data Index: 1577019 (Open Web Text)

Max Activating Token Index: 350

Text #17

Max Range: 1.9713. Min Range: -1.9713

Max Act: 1.9081. Min Act: -0.1700

Data Index: 8606005 (Open Web Text)

Max Activating Token Index: 998

Text #18

Max Range: 1.9713. Min Range: -1.9713

Max Act: 1.9079. Min Act: -0.1700

Data Index: 737244 (Open Web Text)

Max Activating Token Index: 157

Text #19

Max Range: 1.9713. Min Range: -1.9713

Max Act: 1.9037. Min Act: -0.1700

Data Index: 7482703 (Open Web Text)

Max Activating Token Index: 478