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

Dataset: Open Web Text

Neuron 2896 in Layer 0

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: 1.7627. Min Range: -1.7627

Max Act: 1.7627. Min Act: -0.1700

Data Index: 2830214 (Open Web Text)

Max Activating Token Index: 651

Text #1

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.7462. Min Act: -0.1700

Data Index: 1638477 (Open Web Text)

Max Activating Token Index: 716

Text #2

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.7449. Min Act: -0.1700

Data Index: 1876348 (Open Web Text)

Max Activating Token Index: 59

Text #3

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.7287. Min Act: -0.1700

Data Index: 6703205 (Open Web Text)

Max Activating Token Index: 886

Text #4

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.7062. Min Act: -0.1700

Data Index: 6515567 (Open Web Text)

Max Activating Token Index: 990

Text #5

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.7095. Min Act: -0.1700

Data Index: 6106313 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.7118. Min Act: -0.1700

Data Index: 240558 (Open Web Text)

Max Activating Token Index: 153

Text #7

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.6985. Min Act: -0.1700

Data Index: 8616157 (Open Web Text)

Max Activating Token Index: 724

Text #8

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.6989. Min Act: -0.1700

Data Index: 4227289 (Open Web Text)

Max Activating Token Index: 641

Text #9

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.6904. Min Act: -0.1700

Data Index: 8429364 (Open Web Text)

Max Activating Token Index: 675

Text #10

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.6768. Min Act: -0.1700

Data Index: 5298116 (Open Web Text)

Max Activating Token Index: 534

Text #11

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.6799. Min Act: -0.1700

Data Index: 4742550 (Open Web Text)

Max Activating Token Index: 926

Text #12

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.6896. Min Act: -0.1700

Data Index: 5807496 (Open Web Text)

Max Activating Token Index: 782

Text #13

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.6833. Min Act: -0.1700

Data Index: 7814064 (Open Web Text)

Max Activating Token Index: 756

Text #14

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.6797. Min Act: -0.1700

Data Index: 2068079 (Open Web Text)

Max Activating Token Index: 110

Text #15

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.6830. Min Act: -0.1700

Data Index: 199573 (Open Web Text)

Max Activating Token Index: 994

Text #16

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.6854. Min Act: -0.1700

Data Index: 7371766 (Open Web Text)

Max Activating Token Index: 752

Text #17

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.6825. Min Act: -0.1700

Data Index: 5155769 (Open Web Text)

Max Activating Token Index: 868

Text #18

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.6802. Min Act: -0.1700

Data Index: 8459493 (Open Web Text)

Max Activating Token Index: 587

Text #19

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.6700. Min Act: -0.1700

Data Index: 1205393 (Open Web Text)

Max Activating Token Index: 361