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

Dataset: Open Web Text

Neuron 1896 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: 1.9476. Min Range: -1.9476

Max Act: 1.9476. Min Act: -0.1700

Data Index: 5321697 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 1.9476. Min Range: -1.9476

Max Act: 1.7707. Min Act: -0.1700

Data Index: 5768605 (Open Web Text)

Max Activating Token Index: 685

Text #2

Max Range: 1.9476. Min Range: -1.9476

Max Act: 1.7220. Min Act: -0.1700

Data Index: 4197738 (Open Web Text)

Max Activating Token Index: 63

Text #3

Max Range: 1.9476. Min Range: -1.9476

Max Act: 1.7139. Min Act: -0.1700

Data Index: 4516456 (Open Web Text)

Max Activating Token Index: 37

Text #4

Max Range: 1.9476. Min Range: -1.9476

Max Act: 1.7147. Min Act: -0.1700

Data Index: 5214082 (Open Web Text)

Max Activating Token Index: 391

Text #5

Max Range: 1.9476. Min Range: -1.9476

Max Act: 1.7245. Min Act: -0.1700

Data Index: 2317303 (Open Web Text)

Max Activating Token Index: 201

Text #6

Max Range: 1.9476. Min Range: -1.9476

Max Act: 1.7191. Min Act: -0.1700

Data Index: 6279627 (Open Web Text)

Max Activating Token Index: 329

Text #7

Max Range: 1.9476. Min Range: -1.9476

Max Act: 1.7138. Min Act: -0.1700

Data Index: 6134801 (Open Web Text)

Max Activating Token Index: 562

Text #8

Max Range: 1.9476. Min Range: -1.9476

Max Act: 1.7135. Min Act: -0.1700

Data Index: 1069526 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 1.9476. Min Range: -1.9476

Max Act: 1.7015. Min Act: -0.1700

Data Index: 2133144 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 1.9476. Min Range: -1.9476

Max Act: 1.6879. Min Act: -0.1700

Data Index: 3647351 (Open Web Text)

Max Activating Token Index: 38

Text #11

Max Range: 1.9476. Min Range: -1.9476

Max Act: 1.6920. Min Act: -0.1700

Data Index: 6317423 (Open Web Text)

Max Activating Token Index: 11

Text #12

Max Range: 1.9476. Min Range: -1.9476

Max Act: 1.7029. Min Act: -0.1700

Data Index: 7464259 (Open Web Text)

Max Activating Token Index: 19

Text #13

Max Range: 1.9476. Min Range: -1.9476

Max Act: 1.6983. Min Act: -0.1700

Data Index: 911474 (Open Web Text)

Max Activating Token Index: 357

Text #14

Max Range: 1.9476. Min Range: -1.9476

Max Act: 1.7004. Min Act: -0.1700

Data Index: 4859297 (Open Web Text)

Max Activating Token Index: 325

Text #15

Max Range: 1.9476. Min Range: -1.9476

Max Act: 1.6950. Min Act: -0.1700

Data Index: 7487923 (Open Web Text)

Max Activating Token Index: 25

Text #16

Max Range: 1.9476. Min Range: -1.9476

Max Act: 1.6992. Min Act: -0.1700

Data Index: 7592836 (Open Web Text)

Max Activating Token Index: 434

Text #17

Max Range: 1.9476. Min Range: -1.9476

Max Act: 1.6977. Min Act: -0.1700

Data Index: 3699455 (Open Web Text)

Max Activating Token Index: 268

Text #18

Max Range: 1.9476. Min Range: -1.9476

Max Act: 1.7083. Min Act: -0.1700

Data Index: 5739108 (Open Web Text)

Max Activating Token Index: 279

Text #19

Max Range: 1.9476. Min Range: -1.9476

Max Act: 1.6876. Min Act: -0.1700

Data Index: 528845 (Open Web Text)

Max Activating Token Index: 63