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

Dataset: Open Web Text

Neuron 342 in Layer 1

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: 0.9909. Min Range: -0.9909

Max Act: 0.9909. Min Act: -0.1700

Data Index: 8748855 (Open Web Text)

Max Activating Token Index: 21

Text #1

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.9856. Min Act: -0.1700

Data Index: 7469454 (Open Web Text)

Max Activating Token Index: 18

Text #2

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.9106. Min Act: -0.1700

Data Index: 2711775 (Open Web Text)

Max Activating Token Index: 19

Text #3

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.9075. Min Act: -0.1700

Data Index: 3517506 (Open Web Text)

Max Activating Token Index: 19

Text #4

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.8594. Min Act: -0.1700

Data Index: 686166 (Open Web Text)

Max Activating Token Index: 19

Text #5

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.8514. Min Act: -0.1700

Data Index: 7590795 (Open Web Text)

Max Activating Token Index: 20

Text #6

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.8513. Min Act: -0.1700

Data Index: 6470321 (Open Web Text)

Max Activating Token Index: 19

Text #7

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.8498. Min Act: -0.1700

Data Index: 1789120 (Open Web Text)

Max Activating Token Index: 21

Text #8

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.8556. Min Act: -0.1700

Data Index: 1115940 (Open Web Text)

Max Activating Token Index: 16

Text #9

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.8549. Min Act: -0.1700

Data Index: 4891453 (Open Web Text)

Max Activating Token Index: 20

Text #10

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.8413. Min Act: -0.1700

Data Index: 8048183 (Open Web Text)

Max Activating Token Index: 22

Text #11

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.8380. Min Act: -0.1700

Data Index: 1115948 (Open Web Text)

Max Activating Token Index: 19

Text #12

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.8440. Min Act: -0.1700

Data Index: 5510721 (Open Web Text)

Max Activating Token Index: 20

Text #13

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.8369. Min Act: -0.1700

Data Index: 2133585 (Open Web Text)

Max Activating Token Index: 22

Text #14

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.8316. Min Act: -0.1700

Data Index: 8021108 (Open Web Text)

Max Activating Token Index: 23

Text #15

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.8336. Min Act: -0.1700

Data Index: 6818603 (Open Web Text)

Max Activating Token Index: 21

Text #16

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.8208. Min Act: -0.1700

Data Index: 6160737 (Open Web Text)

Max Activating Token Index: 18

Text #17

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.8317. Min Act: -0.1700

Data Index: 5970051 (Open Web Text)

Max Activating Token Index: 19

Text #18

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.8252. Min Act: -0.1700

Data Index: 426576 (Open Web Text)

Max Activating Token Index: 20

Text #19

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.8307. Min Act: -0.1700

Data Index: 5372799 (Open Web Text)

Max Activating Token Index: 20