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

Dataset: Open Web Text

Neuron 1 in Layer 0

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: 2.7630. Min Range: -2.7630

Max Act: 2.7630. Min Act: -0.1700

Data Index: 4434166 (Open Web Text)

Max Activating Token Index: 1015

Text #1

Max Range: 2.7630. Min Range: -2.7630

Max Act: 2.7333. Min Act: -0.1700

Data Index: 2996792 (Open Web Text)

Max Activating Token Index: 786

Text #2

Max Range: 2.7630. Min Range: -2.7630

Max Act: 2.7240. Min Act: -0.1700

Data Index: 4324270 (Open Web Text)

Max Activating Token Index: 17

Text #3

Max Range: 2.7630. Min Range: -2.7630

Max Act: 2.7020. Min Act: -0.1700

Data Index: 4901281 (Open Web Text)

Max Activating Token Index: 737

Text #4

Max Range: 2.7630. Min Range: -2.7630

Max Act: 2.7058. Min Act: -0.1700

Data Index: 1413116 (Open Web Text)

Max Activating Token Index: 70

Text #5

Max Range: 2.7630. Min Range: -2.7630

Max Act: 2.6969. Min Act: -0.1700

Data Index: 433603 (Open Web Text)

Max Activating Token Index: 84

Text #6

Max Range: 2.7630. Min Range: -2.7630

Max Act: 2.7012. Min Act: -0.1700

Data Index: 4802897 (Open Web Text)

Max Activating Token Index: 16

Text #7

Max Range: 2.7630. Min Range: -2.7630

Max Act: 2.6967. Min Act: -0.1700

Data Index: 4298391 (Open Web Text)

Max Activating Token Index: 763

Text #8

Max Range: 2.7630. Min Range: -2.7630

Max Act: 2.7020. Min Act: -0.1700

Data Index: 2937286 (Open Web Text)

Max Activating Token Index: 741

Text #9

Max Range: 2.7630. Min Range: -2.7630

Max Act: 2.7027. Min Act: -0.1700

Data Index: 8689981 (Open Web Text)

Max Activating Token Index: 932

Text #10

Max Range: 2.7630. Min Range: -2.7630

Max Act: 2.6877. Min Act: -0.1700

Data Index: 721443 (Open Web Text)

Max Activating Token Index: 31

Text #11

Max Range: 2.7630. Min Range: -2.7630

Max Act: 2.6870. Min Act: -0.1700

Data Index: 5516581 (Open Web Text)

Max Activating Token Index: 968

Text #12

Max Range: 2.7630. Min Range: -2.7630

Max Act: 2.6860. Min Act: -0.1700

Data Index: 3563028 (Open Web Text)

Max Activating Token Index: 74

Text #13

Max Range: 2.7630. Min Range: -2.7630

Max Act: 2.6715. Min Act: -0.1700

Data Index: 5579745 (Open Web Text)

Max Activating Token Index: 40

Text #14

Max Range: 2.7630. Min Range: -2.7630

Max Act: 2.6741. Min Act: -0.1700

Data Index: 8809036 (Open Web Text)

Max Activating Token Index: 40

Text #15

Max Range: 2.7630. Min Range: -2.7630

Max Act: 2.6627. Min Act: -0.1700

Data Index: 2993853 (Open Web Text)

Max Activating Token Index: 226

Text #16

Max Range: 2.7630. Min Range: -2.7630

Max Act: 2.6576. Min Act: -0.1700

Data Index: 8511298 (Open Web Text)

Max Activating Token Index: 644

Text #17

Max Range: 2.7630. Min Range: -2.7630

Max Act: 2.6576. Min Act: -0.1700

Data Index: 4269425 (Open Web Text)

Max Activating Token Index: 662

Text #18

Max Range: 2.7630. Min Range: -2.7630

Max Act: 2.6648. Min Act: -0.1700

Data Index: 3436952 (Open Web Text)

Max Activating Token Index: 787

Text #19

Max Range: 2.7630. Min Range: -2.7630

Max Act: 2.6595. Min Act: -0.1700

Data Index: 1210956 (Open Web Text)

Max Activating Token Index: 420