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

Dataset: Open Web Text

Neuron 340 in Layer 2

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: 1.9664. Min Range: -1.9664

Max Act: 1.9664. Min Act: -0.1700

Data Index: 381294 (Open Web Text)

Max Activating Token Index: 704

Text #1

Max Range: 1.9664. Min Range: -1.9664

Max Act: 1.9430. Min Act: -0.1700

Data Index: 403933 (Open Web Text)

Max Activating Token Index: 551

Text #2

Max Range: 1.9664. Min Range: -1.9664

Max Act: 1.9313. Min Act: -0.1700

Data Index: 8333208 (Open Web Text)

Max Activating Token Index: 148

Text #3

Max Range: 1.9664. Min Range: -1.9664

Max Act: 1.9324. Min Act: -0.1700

Data Index: 3168185 (Open Web Text)

Max Activating Token Index: 96

Text #4

Max Range: 1.9664. Min Range: -1.9664

Max Act: 1.9418. Min Act: -0.1700

Data Index: 4959296 (Open Web Text)

Max Activating Token Index: 13

Text #5

Max Range: 1.9664. Min Range: -1.9664

Max Act: 1.9438. Min Act: -0.1700

Data Index: 6357006 (Open Web Text)

Max Activating Token Index: 21

Text #6

Max Range: 1.9664. Min Range: -1.9664

Max Act: 1.9206. Min Act: -0.1700

Data Index: 2627395 (Open Web Text)

Max Activating Token Index: 966

Text #7

Max Range: 1.9664. Min Range: -1.9664

Max Act: 1.9230. Min Act: -0.1700

Data Index: 5468825 (Open Web Text)

Max Activating Token Index: 17

Text #8

Max Range: 1.9664. Min Range: -1.9664

Max Act: 1.9089. Min Act: -0.1700

Data Index: 5274586 (Open Web Text)

Max Activating Token Index: 155

Text #9

Max Range: 1.9664. Min Range: -1.9664

Max Act: 1.9182. Min Act: -0.1700

Data Index: 410737 (Open Web Text)

Max Activating Token Index: 95

Text #10

Max Range: 1.9664. Min Range: -1.9664

Max Act: 1.9122. Min Act: -0.1700

Data Index: 7990501 (Open Web Text)

Max Activating Token Index: 563

Text #11

Max Range: 1.9664. Min Range: -1.9664

Max Act: 1.9169. Min Act: -0.1700

Data Index: 256647 (Open Web Text)

Max Activating Token Index: 296

Text #12

Max Range: 1.9664. Min Range: -1.9664

Max Act: 1.9078. Min Act: -0.1700

Data Index: 3752435 (Open Web Text)

Max Activating Token Index: 828

Text #13

Max Range: 1.9664. Min Range: -1.9664

Max Act: 1.9063. Min Act: -0.1700

Data Index: 7560253 (Open Web Text)

Max Activating Token Index: 628

Text #14

Max Range: 1.9664. Min Range: -1.9664

Max Act: 1.9082. Min Act: -0.1700

Data Index: 1314435 (Open Web Text)

Max Activating Token Index: 84

Text #15

Max Range: 1.9664. Min Range: -1.9664

Max Act: 1.9162. Min Act: -0.1700

Data Index: 7074630 (Open Web Text)

Max Activating Token Index: 765

Text #16

Max Range: 1.9664. Min Range: -1.9664

Max Act: 1.9193. Min Act: -0.1700

Data Index: 1314437 (Open Web Text)

Max Activating Token Index: 980

Text #17

Max Range: 1.9664. Min Range: -1.9664

Max Act: 1.8954. Min Act: -0.1700

Data Index: 4844649 (Open Web Text)

Max Activating Token Index: 15

Text #18

Max Range: 1.9664. Min Range: -1.9664

Max Act: 1.8968. Min Act: -0.1700

Data Index: 1695941 (Open Web Text)

Max Activating Token Index: 164

Text #19

Max Range: 1.9664. Min Range: -1.9664

Max Act: 1.9003. Min Act: -0.1700

Data Index: 1701298 (Open Web Text)

Max Activating Token Index: 15