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

Dataset: Open Web Text

Neuron 2345 in Layer 4

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: 2.7988. Min Range: -2.7988

Max Act: 2.7988. Min Act: -0.1700

Data Index: 676698 (Open Web Text)

Max Activating Token Index: 735

Text #1

Max Range: 2.7988. Min Range: -2.7988

Max Act: 2.7774. Min Act: -0.1700

Data Index: 3400717 (Open Web Text)

Max Activating Token Index: 846

Text #2

Max Range: 2.7988. Min Range: -2.7988

Max Act: 2.7317. Min Act: -0.1700

Data Index: 877644 (Open Web Text)

Max Activating Token Index: 814

Text #3

Max Range: 2.7988. Min Range: -2.7988

Max Act: 2.7228. Min Act: -0.1700

Data Index: 4156226 (Open Web Text)

Max Activating Token Index: 528

Text #4

Max Range: 2.7988. Min Range: -2.7988

Max Act: 2.7012. Min Act: -0.1700

Data Index: 6253175 (Open Web Text)

Max Activating Token Index: 842

Text #5

Max Range: 2.7988. Min Range: -2.7988

Max Act: 2.6799. Min Act: -0.1700

Data Index: 1051631 (Open Web Text)

Max Activating Token Index: 332

Text #6

Max Range: 2.7988. Min Range: -2.7988

Max Act: 2.7082. Min Act: -0.1700

Data Index: 3949015 (Open Web Text)

Max Activating Token Index: 845

Text #7

Max Range: 2.7988. Min Range: -2.7988

Max Act: 2.7126. Min Act: -0.1700

Data Index: 1528853 (Open Web Text)

Max Activating Token Index: 909

Text #8

Max Range: 2.7988. Min Range: -2.7988

Max Act: 2.6984. Min Act: -0.1700

Data Index: 2574438 (Open Web Text)

Max Activating Token Index: 108

Text #9

Max Range: 2.7988. Min Range: -2.7988

Max Act: 2.6953. Min Act: -0.1700

Data Index: 5023137 (Open Web Text)

Max Activating Token Index: 833

Text #10

Max Range: 2.7988. Min Range: -2.7988

Max Act: 2.6888. Min Act: -0.1700

Data Index: 4920624 (Open Web Text)

Max Activating Token Index: 423

Text #11

Max Range: 2.7988. Min Range: -2.7988

Max Act: 2.6848. Min Act: -0.1700

Data Index: 5159881 (Open Web Text)

Max Activating Token Index: 423

Text #12

Max Range: 2.7988. Min Range: -2.7988

Max Act: 2.6763. Min Act: -0.1700

Data Index: 4924140 (Open Web Text)

Max Activating Token Index: 371

Text #13

Max Range: 2.7988. Min Range: -2.7988

Max Act: 2.6924. Min Act: -0.1700

Data Index: 3900544 (Open Web Text)

Max Activating Token Index: 423

Text #14

Max Range: 2.7988. Min Range: -2.7988

Max Act: 2.6698. Min Act: -0.1700

Data Index: 3845526 (Open Web Text)

Max Activating Token Index: 330

Text #15

Max Range: 2.7988. Min Range: -2.7988

Max Act: 2.6642. Min Act: -0.1700

Data Index: 4736536 (Open Web Text)

Max Activating Token Index: 845

Text #16

Max Range: 2.7988. Min Range: -2.7988

Max Act: 2.6795. Min Act: -0.1700

Data Index: 4512961 (Open Web Text)

Max Activating Token Index: 493

Text #17

Max Range: 2.7988. Min Range: -2.7988

Max Act: 2.6462. Min Act: -0.1700

Data Index: 520995 (Open Web Text)

Max Activating Token Index: 1007

Text #18

Max Range: 2.7988. Min Range: -2.7988

Max Act: 2.6583. Min Act: -0.1700

Data Index: 3066249 (Open Web Text)

Max Activating Token Index: 159

Text #19

Max Range: 2.7988. Min Range: -2.7988

Max Act: 2.6619. Min Act: -0.1700

Data Index: 4943751 (Open Web Text)

Max Activating Token Index: 852