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

Dataset: Open Web Text

Neuron 2661 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: 1.9941. Min Range: -1.9941

Max Act: 1.9941. Min Act: -0.1700

Data Index: 6446569 (Open Web Text)

Max Activating Token Index: 14

Text #1

Max Range: 1.9941. Min Range: -1.9941

Max Act: 1.9826. Min Act: -0.1700

Data Index: 7672540 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 1.9941. Min Range: -1.9941

Max Act: 1.9889. Min Act: -0.1700

Data Index: 3057823 (Open Web Text)

Max Activating Token Index: 17

Text #3

Max Range: 1.9941. Min Range: -1.9941

Max Act: 1.9878. Min Act: -0.1700

Data Index: 3138542 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 1.9941. Min Range: -1.9941

Max Act: 1.9326. Min Act: -0.1700

Data Index: 488937 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 1.9941. Min Range: -1.9941

Max Act: 1.9380. Min Act: -0.1700

Data Index: 7138753 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 1.9941. Min Range: -1.9941

Max Act: 1.9424. Min Act: -0.1700

Data Index: 3545937 (Open Web Text)

Max Activating Token Index: 46

Text #7

Max Range: 1.9941. Min Range: -1.9941

Max Act: 1.9202. Min Act: -0.1700

Data Index: 5838465 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 1.9941. Min Range: -1.9941

Max Act: 1.9166. Min Act: -0.1700

Data Index: 5273458 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 1.9941. Min Range: -1.9941

Max Act: 1.9081. Min Act: -0.1700

Data Index: 5600233 (Open Web Text)

Max Activating Token Index: 14

Text #10

Max Range: 1.9941. Min Range: -1.9941

Max Act: 1.8989. Min Act: -0.1700

Data Index: 379086 (Open Web Text)

Max Activating Token Index: 982

Text #11

Max Range: 1.9941. Min Range: -1.9941

Max Act: 1.9018. Min Act: -0.1700

Data Index: 8640202 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 1.9941. Min Range: -1.9941

Max Act: 1.9044. Min Act: -0.1700

Data Index: 1248687 (Open Web Text)

Max Activating Token Index: 260

Text #13

Max Range: 1.9941. Min Range: -1.9941

Max Act: 1.8960. Min Act: -0.1700

Data Index: 1303761 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 1.9941. Min Range: -1.9941

Max Act: 1.9063. Min Act: -0.1700

Data Index: 2580545 (Open Web Text)

Max Activating Token Index: 22

Text #15

Max Range: 1.9941. Min Range: -1.9941

Max Act: 1.9089. Min Act: -0.1700

Data Index: 351235 (Open Web Text)

Max Activating Token Index: 641

Text #16

Max Range: 1.9941. Min Range: -1.9941

Max Act: 1.9003. Min Act: -0.1700

Data Index: 455473 (Open Web Text)

Max Activating Token Index: 31

Text #17

Max Range: 1.9941. Min Range: -1.9941

Max Act: 1.8962. Min Act: -0.1700

Data Index: 4828209 (Open Web Text)

Max Activating Token Index: 9

Text #18

Max Range: 1.9941. Min Range: -1.9941

Max Act: 1.8847. Min Act: -0.1700

Data Index: 755354 (Open Web Text)

Max Activating Token Index: 345

Text #19

Max Range: 1.9941. Min Range: -1.9941

Max Act: 1.8909. Min Act: -0.1700

Data Index: 3963151 (Open Web Text)

Max Activating Token Index: 6