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

Dataset: Open Web Text

Neuron 29 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: 3.7783. Min Range: -3.7783

Max Act: 3.7730. Min Act: -0.1700

Data Index: 4693973 (Open Web Text)

Max Activating Token Index: 987

Text #1

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.7699. Min Act: -0.1700

Data Index: 4314672 (Open Web Text)

Max Activating Token Index: 417

Text #2

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.7783. Min Act: -0.1700

Data Index: 3283342 (Open Web Text)

Max Activating Token Index: 897

Text #3

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.7437. Min Act: -0.1700

Data Index: 2369409 (Open Web Text)

Max Activating Token Index: 524

Text #4

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.7422. Min Act: -0.1700

Data Index: 3724369 (Open Web Text)

Max Activating Token Index: 1007

Text #5

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.7447. Min Act: -0.1700

Data Index: 4135434 (Open Web Text)

Max Activating Token Index: 721

Text #6

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.7302. Min Act: -0.1700

Data Index: 6980462 (Open Web Text)

Max Activating Token Index: 294

Text #7

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.7284. Min Act: -0.1700

Data Index: 3981332 (Open Web Text)

Max Activating Token Index: 571

Text #8

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.7153. Min Act: -0.1700

Data Index: 3839149 (Open Web Text)

Max Activating Token Index: 846

Text #9

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.7178. Min Act: -0.1700

Data Index: 3101976 (Open Web Text)

Max Activating Token Index: 543

Text #10

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.7027. Min Act: -0.1700

Data Index: 3478933 (Open Web Text)

Max Activating Token Index: 942

Text #11

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.6994. Min Act: -0.1700

Data Index: 6716523 (Open Web Text)

Max Activating Token Index: 622

Text #12

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.7135. Min Act: -0.1700

Data Index: 958613 (Open Web Text)

Max Activating Token Index: 900

Text #13

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.6988. Min Act: -0.1700

Data Index: 883088 (Open Web Text)

Max Activating Token Index: 474

Text #14

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.7130. Min Act: -0.1700

Data Index: 6713813 (Open Web Text)

Max Activating Token Index: 735

Text #15

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.7208. Min Act: -0.1700

Data Index: 1190166 (Open Web Text)

Max Activating Token Index: 137

Text #16

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.7014. Min Act: -0.1700

Data Index: 3828978 (Open Web Text)

Max Activating Token Index: 618

Text #17

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.7085. Min Act: -0.1700

Data Index: 6633191 (Open Web Text)

Max Activating Token Index: 170

Text #18

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.7042. Min Act: -0.1700

Data Index: 2400947 (Open Web Text)

Max Activating Token Index: 208

Text #19

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.7058. Min Act: -0.1700

Data Index: 5127069 (Open Web Text)

Max Activating Token Index: 1020