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

Dataset: Open Web Text

Neuron 2283 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: 4.1618. Min Range: -4.1618

Max Act: 4.1618. Min Act: -0.1700

Data Index: 5189724 (Open Web Text)

Max Activating Token Index: 962

Text #1

Max Range: 4.1618. Min Range: -4.1618

Max Act: 4.1128. Min Act: -0.1700

Data Index: 5299860 (Open Web Text)

Max Activating Token Index: 203

Text #2

Max Range: 4.1618. Min Range: -4.1618

Max Act: 4.0891. Min Act: -0.1700

Data Index: 3812675 (Open Web Text)

Max Activating Token Index: 288

Text #3

Max Range: 4.1618. Min Range: -4.1618

Max Act: 4.0754. Min Act: -0.1700

Data Index: 3812674 (Open Web Text)

Max Activating Token Index: 749

Text #4

Max Range: 4.1618. Min Range: -4.1618

Max Act: 4.0225. Min Act: -0.1700

Data Index: 4001949 (Open Web Text)

Max Activating Token Index: 779

Text #5

Max Range: 4.1618. Min Range: -4.1618

Max Act: 3.9821. Min Act: -0.1700

Data Index: 3287457 (Open Web Text)

Max Activating Token Index: 997

Text #6

Max Range: 4.1618. Min Range: -4.1618

Max Act: 3.9643. Min Act: -0.1700

Data Index: 6735950 (Open Web Text)

Max Activating Token Index: 504

Text #7

Max Range: 4.1618. Min Range: -4.1618

Max Act: 3.9513. Min Act: -0.1700

Data Index: 2929516 (Open Web Text)

Max Activating Token Index: 1003

Text #8

Max Range: 4.1618. Min Range: -4.1618

Max Act: 3.9541. Min Act: -0.1700

Data Index: 2374914 (Open Web Text)

Max Activating Token Index: 115

Text #9

Max Range: 4.1618. Min Range: -4.1618

Max Act: 3.9488. Min Act: -0.1700

Data Index: 3417859 (Open Web Text)

Max Activating Token Index: 244

Text #10

Max Range: 4.1618. Min Range: -4.1618

Max Act: 3.9210. Min Act: -0.1700

Data Index: 2011334 (Open Web Text)

Max Activating Token Index: 376

Text #11

Max Range: 4.1618. Min Range: -4.1618

Max Act: 3.8928. Min Act: -0.1700

Data Index: 7874100 (Open Web Text)

Max Activating Token Index: 1003

Text #12

Max Range: 4.1618. Min Range: -4.1618

Max Act: 3.9195. Min Act: -0.1700

Data Index: 4736586 (Open Web Text)

Max Activating Token Index: 859

Text #13

Max Range: 4.1618. Min Range: -4.1618

Max Act: 3.8919. Min Act: -0.1700

Data Index: 7814200 (Open Web Text)

Max Activating Token Index: 187

Text #14

Max Range: 4.1618. Min Range: -4.1618

Max Act: 3.9072. Min Act: -0.1700

Data Index: 2929517 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 4.1618. Min Range: -4.1618

Max Act: 3.8847. Min Act: -0.1700

Data Index: 4676121 (Open Web Text)

Max Activating Token Index: 561

Text #16

Max Range: 4.1618. Min Range: -4.1618

Max Act: 3.8815. Min Act: -0.1700

Data Index: 1628002 (Open Web Text)

Max Activating Token Index: 642

Text #17

Max Range: 4.1618. Min Range: -4.1618

Max Act: 3.8520. Min Act: -0.1700

Data Index: 3004132 (Open Web Text)

Max Activating Token Index: 441

Text #18

Max Range: 4.1618. Min Range: -4.1618

Max Act: 3.8670. Min Act: -0.1700

Data Index: 3111219 (Open Web Text)

Max Activating Token Index: 126

Text #19

Max Range: 4.1618. Min Range: -4.1618

Max Act: 3.8723. Min Act: -0.1700

Data Index: 39254 (Open Web Text)

Max Activating Token Index: 141