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

Dataset: Open Web Text

Neuron 1993 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: 10.2463. Min Range: -10.2463

Max Act: 10.2463. Min Act: -0.1700

Data Index: 7189028 (Open Web Text)

Max Activating Token Index: 585

Text #1

Max Range: 10.2463. Min Range: -10.2463

Max Act: 10.0147. Min Act: -0.1700

Data Index: 7892449 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 10.2463. Min Range: -10.2463

Max Act: 9.9363. Min Act: -0.1700

Data Index: 4325852 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 10.2463. Min Range: -10.2463

Max Act: 9.7685. Min Act: -0.1700

Data Index: 338122 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 10.2463. Min Range: -10.2463

Max Act: 9.7377. Min Act: -0.1700

Data Index: 1358448 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 10.2463. Min Range: -10.2463

Max Act: 9.7020. Min Act: -0.1700

Data Index: 6268692 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 10.2463. Min Range: -10.2463

Max Act: 9.7718. Min Act: -0.1700

Data Index: 6293931 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 10.2463. Min Range: -10.2463

Max Act: 9.6536. Min Act: -0.1700

Data Index: 1779047 (Open Web Text)

Max Activating Token Index: 1010

Text #8

Max Range: 10.2463. Min Range: -10.2463

Max Act: 9.7546. Min Act: -0.1700

Data Index: 1548809 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 10.2463. Min Range: -10.2463

Max Act: 9.6094. Min Act: -0.1700

Data Index: 5972354 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 10.2463. Min Range: -10.2463

Max Act: 9.5989. Min Act: -0.1700

Data Index: 7926902 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 10.2463. Min Range: -10.2463

Max Act: 9.7184. Min Act: -0.1700

Data Index: 5805187 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 10.2463. Min Range: -10.2463

Max Act: 9.6126. Min Act: -0.1700

Data Index: 1670403 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 10.2463. Min Range: -10.2463

Max Act: 9.6157. Min Act: -0.1700

Data Index: 7280787 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 10.2463. Min Range: -10.2463

Max Act: 9.5946. Min Act: -0.1700

Data Index: 2897127 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 10.2463. Min Range: -10.2463

Max Act: 9.5909. Min Act: -0.1700

Data Index: 5831667 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 10.2463. Min Range: -10.2463

Max Act: 9.5883. Min Act: -0.1700

Data Index: 3303058 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 10.2463. Min Range: -10.2463

Max Act: 9.5698. Min Act: -0.1700

Data Index: 3258151 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 10.2463. Min Range: -10.2463

Max Act: 9.6300. Min Act: -0.1700

Data Index: 7124652 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 10.2463. Min Range: -10.2463

Max Act: 9.5567. Min Act: -0.1700

Data Index: 1109263 (Open Web Text)

Max Activating Token Index: 1023