Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 656 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')

Text #0

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.8320. Min Act: -0.1700

Data Index: 622033 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.8007. Min Act: -0.1700

Data Index: 5400639 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.7694. Min Act: -0.1700

Data Index: 7132931 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.7694. Min Act: -0.1700

Data Index: 1914395 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.7694. Min Act: -0.1700

Data Index: 2727487 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.7381. Min Act: -0.1700

Data Index: 8410456 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.7694. Min Act: -0.1700

Data Index: 80571 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.7381. Min Act: -0.1700

Data Index: 332816 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.7381. Min Act: -0.1700

Data Index: 2474710 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.7068. Min Act: -0.1700

Data Index: 2135793 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.6756. Min Act: -0.1700

Data Index: 940367 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.6443. Min Act: -0.1700

Data Index: 482912 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.6443. Min Act: -0.1700

Data Index: 3419070 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.6443. Min Act: -0.1700

Data Index: 3429009 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.6443. Min Act: -0.1700

Data Index: 227433 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.6443. Min Act: -0.1700

Data Index: 8220806 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.6443. Min Act: -0.1700

Data Index: 913231 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.6130. Min Act: -0.1700

Data Index: 6267020 (Open Web Text)

Max Activating Token Index: 104

Text #18

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.6130. Min Act: -0.1700

Data Index: 7691806 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.5817. Min Act: -0.1700

Data Index: 6454952 (Open Web Text)

Max Activating Token Index: 594