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

Dataset: Open Web Text

Neuron 1131 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: 1.7882. Min Range: -1.7882

Max Act: 1.7882. Min Act: -0.1700

Data Index: 7958618 (Open Web Text)

Max Activating Token Index: 13

Text #1

Max Range: 1.7882. Min Range: -1.7882

Max Act: 1.7550. Min Act: -0.1693

Data Index: 7021600 (Open Web Text)

Max Activating Token Index: 967

Text #2

Max Range: 1.7882. Min Range: -1.7882

Max Act: 1.7467. Min Act: -0.1697

Data Index: 5078746 (Open Web Text)

Max Activating Token Index: 13

Text #3

Max Range: 1.7882. Min Range: -1.7882

Max Act: 1.7539. Min Act: -0.1700

Data Index: 5088123 (Open Web Text)

Max Activating Token Index: 10

Text #4

Max Range: 1.7882. Min Range: -1.7882

Max Act: 1.7332. Min Act: -0.1684

Data Index: 1495052 (Open Web Text)

Max Activating Token Index: 15

Text #5

Max Range: 1.7882. Min Range: -1.7882

Max Act: 1.7294. Min Act: -0.1699

Data Index: 333811 (Open Web Text)

Max Activating Token Index: 13

Text #6

Max Range: 1.7882. Min Range: -1.7882

Max Act: 1.7067. Min Act: -0.1700

Data Index: 1935232 (Open Web Text)

Max Activating Token Index: 21

Text #7

Max Range: 1.7882. Min Range: -1.7882

Max Act: 1.7174. Min Act: -0.1692

Data Index: 6647211 (Open Web Text)

Max Activating Token Index: 1021

Text #8

Max Range: 1.7882. Min Range: -1.7882

Max Act: 1.7046. Min Act: -0.1700

Data Index: 8271314 (Open Web Text)

Max Activating Token Index: 13

Text #9

Max Range: 1.7882. Min Range: -1.7882

Max Act: 1.7080. Min Act: -0.1700

Data Index: 1690121 (Open Web Text)

Max Activating Token Index: 15

Text #10

Max Range: 1.7882. Min Range: -1.7882

Max Act: 1.6993. Min Act: -0.1700

Data Index: 1278214 (Open Web Text)

Max Activating Token Index: 983

Text #11

Max Range: 1.7882. Min Range: -1.7882

Max Act: 1.7116. Min Act: -0.1699

Data Index: 3651206 (Open Web Text)

Max Activating Token Index: 1019

Text #12

Max Range: 1.7882. Min Range: -1.7882

Max Act: 1.6928. Min Act: -0.1700

Data Index: 7900197 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 1.7882. Min Range: -1.7882

Max Act: 1.7001. Min Act: -0.1662

Data Index: 7518064 (Open Web Text)

Max Activating Token Index: 19

Text #14

Max Range: 1.7882. Min Range: -1.7882

Max Act: 1.6949. Min Act: -0.1700

Data Index: 2582516 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 1.7882. Min Range: -1.7882

Max Act: 1.6875. Min Act: -0.1661

Data Index: 1841847 (Open Web Text)

Max Activating Token Index: 691

Text #16

Max Range: 1.7882. Min Range: -1.7882

Max Act: 1.6997. Min Act: -0.1658

Data Index: 4568893 (Open Web Text)

Max Activating Token Index: 33

Text #17

Max Range: 1.7882. Min Range: -1.7882

Max Act: 1.6995. Min Act: -0.1690

Data Index: 4291409 (Open Web Text)

Max Activating Token Index: 616

Text #18

Max Range: 1.7882. Min Range: -1.7882

Max Act: 1.7000. Min Act: -0.1698

Data Index: 8185197 (Open Web Text)

Max Activating Token Index: 12

Text #19

Max Range: 1.7882. Min Range: -1.7882

Max Act: 1.6928. Min Act: -0.1700

Data Index: 4131992 (Open Web Text)

Max Activating Token Index: 21