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

Dataset: Open Web Text

Neuron 2869 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: 4.3718. Min Range: -4.3718

Max Act: 4.3718. Min Act: -0.1700

Data Index: 4052011 (Open Web Text)

Max Activating Token Index: 1010

Text #1

Max Range: 4.3718. Min Range: -4.3718

Max Act: 4.2894. Min Act: -0.1700

Data Index: 4255509 (Open Web Text)

Max Activating Token Index: 997

Text #2

Max Range: 4.3718. Min Range: -4.3718

Max Act: 4.2575. Min Act: -0.1700

Data Index: 3834225 (Open Web Text)

Max Activating Token Index: 59

Text #3

Max Range: 4.3718. Min Range: -4.3718

Max Act: 4.3136. Min Act: -0.1700

Data Index: 3635149 (Open Web Text)

Max Activating Token Index: 728

Text #4

Max Range: 4.3718. Min Range: -4.3718

Max Act: 4.3230. Min Act: -0.1700

Data Index: 3285398 (Open Web Text)

Max Activating Token Index: 965

Text #5

Max Range: 4.3718. Min Range: -4.3718

Max Act: 4.3195. Min Act: -0.1700

Data Index: 675112 (Open Web Text)

Max Activating Token Index: 917

Text #6

Max Range: 4.3718. Min Range: -4.3718

Max Act: 4.2617. Min Act: -0.1700

Data Index: 6373603 (Open Web Text)

Max Activating Token Index: 783

Text #7

Max Range: 4.3718. Min Range: -4.3718

Max Act: 4.2822. Min Act: -0.1700

Data Index: 6541811 (Open Web Text)

Max Activating Token Index: 764

Text #8

Max Range: 4.3718. Min Range: -4.3718

Max Act: 4.2361. Min Act: -0.1700

Data Index: 2327430 (Open Web Text)

Max Activating Token Index: 147

Text #9

Max Range: 4.3718. Min Range: -4.3718

Max Act: 4.2635. Min Act: -0.1700

Data Index: 2171398 (Open Web Text)

Max Activating Token Index: 64

Text #10

Max Range: 4.3718. Min Range: -4.3718

Max Act: 4.2972. Min Act: -0.1700

Data Index: 7502492 (Open Web Text)

Max Activating Token Index: 450

Text #11

Max Range: 4.3718. Min Range: -4.3718

Max Act: 4.1997. Min Act: -0.1700

Data Index: 6540157 (Open Web Text)

Max Activating Token Index: 77

Text #12

Max Range: 4.3718. Min Range: -4.3718

Max Act: 4.2610. Min Act: -0.1700

Data Index: 5521924 (Open Web Text)

Max Activating Token Index: 427

Text #13

Max Range: 4.3718. Min Range: -4.3718

Max Act: 4.2473. Min Act: -0.1700

Data Index: 7165095 (Open Web Text)

Max Activating Token Index: 912

Text #14

Max Range: 4.3718. Min Range: -4.3718

Max Act: 4.1919. Min Act: -0.1700

Data Index: 2931556 (Open Web Text)

Max Activating Token Index: 884

Text #15

Max Range: 4.3718. Min Range: -4.3718

Max Act: 4.1755. Min Act: -0.1700

Data Index: 2495972 (Open Web Text)

Max Activating Token Index: 404

Text #16

Max Range: 4.3718. Min Range: -4.3718

Max Act: 4.1514. Min Act: -0.1700

Data Index: 2139448 (Open Web Text)

Max Activating Token Index: 897

Text #17

Max Range: 4.3718. Min Range: -4.3718

Max Act: 4.2133. Min Act: -0.1700

Data Index: 4721194 (Open Web Text)

Max Activating Token Index: 557

Text #18

Max Range: 4.3718. Min Range: -4.3718

Max Act: 4.1714. Min Act: -0.1700

Data Index: 5637032 (Open Web Text)

Max Activating Token Index: 69

Text #19

Max Range: 4.3718. Min Range: -4.3718

Max Act: 4.2122. Min Act: -0.1700

Data Index: 1076084 (Open Web Text)

Max Activating Token Index: 717