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

Dataset: Open Web Text

Neuron 172 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: 1.1643. Min Range: -1.1643

Max Act: 1.1643. Min Act: -0.1700

Data Index: 7874441 (Open Web Text)

Max Activating Token Index: 1022

Text #1

Max Range: 1.1643. Min Range: -1.1643

Max Act: 1.1489. Min Act: -0.1700

Data Index: 1092372 (Open Web Text)

Max Activating Token Index: 1020

Text #2

Max Range: 1.1643. Min Range: -1.1643

Max Act: 1.1476. Min Act: -0.1700

Data Index: 2326638 (Open Web Text)

Max Activating Token Index: 1021

Text #3

Max Range: 1.1643. Min Range: -1.1643

Max Act: 1.1534. Min Act: -0.1700

Data Index: 5155147 (Open Web Text)

Max Activating Token Index: 1022

Text #4

Max Range: 1.1643. Min Range: -1.1643

Max Act: 1.1296. Min Act: -0.1700

Data Index: 8336236 (Open Web Text)

Max Activating Token Index: 1022

Text #5

Max Range: 1.1643. Min Range: -1.1643

Max Act: 1.1366. Min Act: -0.1700

Data Index: 7690706 (Open Web Text)

Max Activating Token Index: 1022

Text #6

Max Range: 1.1643. Min Range: -1.1643

Max Act: 1.1332. Min Act: -0.1700

Data Index: 3283145 (Open Web Text)

Max Activating Token Index: 1020

Text #7

Max Range: 1.1643. Min Range: -1.1643

Max Act: 1.1164. Min Act: -0.1700

Data Index: 396794 (Open Web Text)

Max Activating Token Index: 1022

Text #8

Max Range: 1.1643. Min Range: -1.1643

Max Act: 1.1251. Min Act: -0.1700

Data Index: 5397024 (Open Web Text)

Max Activating Token Index: 1022

Text #9

Max Range: 1.1643. Min Range: -1.1643

Max Act: 1.1214. Min Act: -0.1700

Data Index: 5213601 (Open Web Text)

Max Activating Token Index: 1022

Text #10

Max Range: 1.1643. Min Range: -1.1643

Max Act: 1.1280. Min Act: -0.1700

Data Index: 4831556 (Open Web Text)

Max Activating Token Index: 1021

Text #11

Max Range: 1.1643. Min Range: -1.1643

Max Act: 1.1215. Min Act: -0.1700

Data Index: 1458109 (Open Web Text)

Max Activating Token Index: 1022

Text #12

Max Range: 1.1643. Min Range: -1.1643

Max Act: 1.1162. Min Act: -0.1700

Data Index: 1598239 (Open Web Text)

Max Activating Token Index: 1019

Text #13

Max Range: 1.1643. Min Range: -1.1643

Max Act: 1.1128. Min Act: -0.1700

Data Index: 4897595 (Open Web Text)

Max Activating Token Index: 1021

Text #14

Max Range: 1.1643. Min Range: -1.1643

Max Act: 1.1147. Min Act: -0.1700

Data Index: 3578133 (Open Web Text)

Max Activating Token Index: 1018

Text #15

Max Range: 1.1643. Min Range: -1.1643

Max Act: 1.1057. Min Act: -0.1700

Data Index: 5461942 (Open Web Text)

Max Activating Token Index: 1022

Text #16

Max Range: 1.1643. Min Range: -1.1643

Max Act: 1.1025. Min Act: -0.1700

Data Index: 7262803 (Open Web Text)

Max Activating Token Index: 1022

Text #17

Max Range: 1.1643. Min Range: -1.1643

Max Act: 1.1079. Min Act: -0.1700

Data Index: 6980677 (Open Web Text)

Max Activating Token Index: 1020

Text #18

Max Range: 1.1643. Min Range: -1.1643

Max Act: 1.1000. Min Act: -0.1700

Data Index: 6618021 (Open Web Text)

Max Activating Token Index: 1022

Text #19

Max Range: 1.1643. Min Range: -1.1643

Max Act: 1.1024. Min Act: -0.1700

Data Index: 5941373 (Open Web Text)

Max Activating Token Index: 1022