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

Dataset: Open Web Text

Neuron 1647 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: 1.8830. Min Range: -1.8830

Max Act: 1.8830. Min Act: -0.1700

Data Index: 6608596 (Open Web Text)

Max Activating Token Index: 374

Text #1

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.8183. Min Act: -0.1700

Data Index: 536516 (Open Web Text)

Max Activating Token Index: 1020

Text #2

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.8295. Min Act: -0.1700

Data Index: 1449707 (Open Web Text)

Max Activating Token Index: 1008

Text #3

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.8151. Min Act: -0.1700

Data Index: 2619795 (Open Web Text)

Max Activating Token Index: 10

Text #4

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.8273. Min Act: -0.1700

Data Index: 7045411 (Open Web Text)

Max Activating Token Index: 23

Text #5

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.8241. Min Act: -0.1700

Data Index: 1234694 (Open Web Text)

Max Activating Token Index: 1021

Text #6

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.8208. Min Act: -0.1700

Data Index: 5961287 (Open Web Text)

Max Activating Token Index: 12

Text #7

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.7912. Min Act: -0.1700

Data Index: 5005537 (Open Web Text)

Max Activating Token Index: 723

Text #8

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.8145. Min Act: -0.1700

Data Index: 4886966 (Open Web Text)

Max Activating Token Index: 62

Text #9

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.8018. Min Act: -0.1700

Data Index: 2841644 (Open Web Text)

Max Activating Token Index: 26

Text #10

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.8001. Min Act: -0.1699

Data Index: 4658742 (Open Web Text)

Max Activating Token Index: 395

Text #11

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.7922. Min Act: -0.1700

Data Index: 4815183 (Open Web Text)

Max Activating Token Index: 1006

Text #12

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.7964. Min Act: -0.1700

Data Index: 5987683 (Open Web Text)

Max Activating Token Index: 17

Text #13

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.7917. Min Act: -0.1700

Data Index: 7632246 (Open Web Text)

Max Activating Token Index: 12

Text #14

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.7928. Min Act: -0.1700

Data Index: 3352994 (Open Web Text)

Max Activating Token Index: 13

Text #15

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.7771. Min Act: -0.1700

Data Index: 4973778 (Open Web Text)

Max Activating Token Index: 15

Text #16

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.7767. Min Act: -0.1700

Data Index: 1137960 (Open Web Text)

Max Activating Token Index: 427

Text #17

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.7884. Min Act: -0.1697

Data Index: 2389423 (Open Web Text)

Max Activating Token Index: 980

Text #18

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.7776. Min Act: -0.1700

Data Index: 2811749 (Open Web Text)

Max Activating Token Index: 46

Text #19

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.7683. Min Act: -0.1700

Data Index: 5579444 (Open Web Text)

Max Activating Token Index: 972