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

Dataset: Open Web Text

Neuron 96 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: 1.8037. Min Range: -1.8037

Max Act: 1.8037. Min Act: -0.1698

Data Index: 7957928 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 1.8037. Min Range: -1.8037

Max Act: 1.7355. Min Act: -0.1691

Data Index: 5125033 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 1.8037. Min Range: -1.8037

Max Act: 1.7427. Min Act: -0.1700

Data Index: 5120143 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 1.8037. Min Range: -1.8037

Max Act: 1.7240. Min Act: -0.1696

Data Index: 5926658 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 1.8037. Min Range: -1.8037

Max Act: 1.7161. Min Act: -0.1664

Data Index: 1352553 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 1.8037. Min Range: -1.8037

Max Act: 1.7286. Min Act: -0.1691

Data Index: 3858981 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 1.8037. Min Range: -1.8037

Max Act: 1.7109. Min Act: -0.1691

Data Index: 5471479 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 1.8037. Min Range: -1.8037

Max Act: 1.7145. Min Act: -0.1698

Data Index: 7585237 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 1.8037. Min Range: -1.8037

Max Act: 1.7128. Min Act: -0.1695

Data Index: 4207095 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 1.8037. Min Range: -1.8037

Max Act: 1.6910. Min Act: -0.1700

Data Index: 7559999 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 1.8037. Min Range: -1.8037

Max Act: 1.6874. Min Act: -0.1659

Data Index: 8734706 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 1.8037. Min Range: -1.8037

Max Act: 1.6781. Min Act: -0.1682

Data Index: 5936771 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 1.8037. Min Range: -1.8037

Max Act: 1.6792. Min Act: -0.1699

Data Index: 1744734 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 1.8037. Min Range: -1.8037

Max Act: 1.6770. Min Act: -0.1700

Data Index: 6627699 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 1.8037. Min Range: -1.8037

Max Act: 1.6737. Min Act: -0.1699

Data Index: 693741 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 1.8037. Min Range: -1.8037

Max Act: 1.6867. Min Act: -0.1684

Data Index: 163535 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 1.8037. Min Range: -1.8037

Max Act: 1.6660. Min Act: -0.1690

Data Index: 3077471 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 1.8037. Min Range: -1.8037

Max Act: 1.6530. Min Act: -0.1679

Data Index: 4589310 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 1.8037. Min Range: -1.8037

Max Act: 1.6679. Min Act: -0.1673

Data Index: 1491787 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 1.8037. Min Range: -1.8037

Max Act: 1.6635. Min Act: -0.1679

Data Index: 1637960 (Open Web Text)

Max Activating Token Index: 1023