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

Dataset: Open Web Text

Neuron 1634 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: 4.0007. Min Range: -4.0007

Max Act: 4.0007. Min Act: -0.1700

Data Index: 2213516 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 4.0007. Min Range: -4.0007

Max Act: 3.8921. Min Act: -0.1700

Data Index: 4029826 (Open Web Text)

Max Activating Token Index: 796

Text #2

Max Range: 4.0007. Min Range: -4.0007

Max Act: 3.8853. Min Act: -0.1700

Data Index: 441816 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.0007. Min Range: -4.0007

Max Act: 3.8959. Min Act: -0.1700

Data Index: 1307587 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.0007. Min Range: -4.0007

Max Act: 3.8998. Min Act: -0.1700

Data Index: 3208195 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.0007. Min Range: -4.0007

Max Act: 3.8502. Min Act: -0.1700

Data Index: 8208453 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 4.0007. Min Range: -4.0007

Max Act: 3.8405. Min Act: -0.1700

Data Index: 6545015 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 4.0007. Min Range: -4.0007

Max Act: 3.8231. Min Act: -0.1700

Data Index: 834191 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 4.0007. Min Range: -4.0007

Max Act: 3.8203. Min Act: -0.1700

Data Index: 3257903 (Open Web Text)

Max Activating Token Index: 1004

Text #9

Max Range: 4.0007. Min Range: -4.0007

Max Act: 3.8283. Min Act: -0.1700

Data Index: 1347419 (Open Web Text)

Max Activating Token Index: 1010

Text #10

Max Range: 4.0007. Min Range: -4.0007

Max Act: 3.7935. Min Act: -0.1700

Data Index: 3576065 (Open Web Text)

Max Activating Token Index: 1020

Text #11

Max Range: 4.0007. Min Range: -4.0007

Max Act: 3.7904. Min Act: -0.1700

Data Index: 861489 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 4.0007. Min Range: -4.0007

Max Act: 3.7952. Min Act: -0.1700

Data Index: 3149422 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 4.0007. Min Range: -4.0007

Max Act: 3.7825. Min Act: -0.1700

Data Index: 3412042 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 4.0007. Min Range: -4.0007

Max Act: 3.7589. Min Act: -0.1700

Data Index: 1569922 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 4.0007. Min Range: -4.0007

Max Act: 3.7613. Min Act: -0.1700

Data Index: 2868776 (Open Web Text)

Max Activating Token Index: 1016

Text #16

Max Range: 4.0007. Min Range: -4.0007

Max Act: 3.7768. Min Act: -0.1700

Data Index: 2723129 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 4.0007. Min Range: -4.0007

Max Act: 3.7618. Min Act: -0.1700

Data Index: 486717 (Open Web Text)

Max Activating Token Index: 828

Text #18

Max Range: 4.0007. Min Range: -4.0007

Max Act: 3.7843. Min Act: -0.1700

Data Index: 2353630 (Open Web Text)

Max Activating Token Index: 10

Text #19

Max Range: 4.0007. Min Range: -4.0007

Max Act: 3.7664. Min Act: -0.1700

Data Index: 979768 (Open Web Text)

Max Activating Token Index: 991