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

Dataset: Open Web Text

Neuron 636 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: 2.3360. Min Range: -2.3360

Max Act: 2.3360. Min Act: -0.1700

Data Index: 2173415 (Open Web Text)

Max Activating Token Index: 1022

Text #1

Max Range: 2.3360. Min Range: -2.3360

Max Act: 2.2981. Min Act: -0.1700

Data Index: 6649789 (Open Web Text)

Max Activating Token Index: 1022

Text #2

Max Range: 2.3360. Min Range: -2.3360

Max Act: 2.2590. Min Act: -0.1700

Data Index: 4259290 (Open Web Text)

Max Activating Token Index: 1022

Text #3

Max Range: 2.3360. Min Range: -2.3360

Max Act: 2.2540. Min Act: -0.1700

Data Index: 4068712 (Open Web Text)

Max Activating Token Index: 1022

Text #4

Max Range: 2.3360. Min Range: -2.3360

Max Act: 2.2234. Min Act: -0.1700

Data Index: 8748576 (Open Web Text)

Max Activating Token Index: 1021

Text #5

Max Range: 2.3360. Min Range: -2.3360

Max Act: 2.2184. Min Act: -0.1700

Data Index: 2160916 (Open Web Text)

Max Activating Token Index: 1022

Text #6

Max Range: 2.3360. Min Range: -2.3360

Max Act: 2.2389. Min Act: -0.1700

Data Index: 640439 (Open Web Text)

Max Activating Token Index: 1022

Text #7

Max Range: 2.3360. Min Range: -2.3360

Max Act: 2.2486. Min Act: -0.1700

Data Index: 7068635 (Open Web Text)

Max Activating Token Index: 1021

Text #8

Max Range: 2.3360. Min Range: -2.3360

Max Act: 2.2205. Min Act: -0.1700

Data Index: 5158852 (Open Web Text)

Max Activating Token Index: 1022

Text #9

Max Range: 2.3360. Min Range: -2.3360

Max Act: 2.2137. Min Act: -0.1700

Data Index: 5596399 (Open Web Text)

Max Activating Token Index: 1022

Text #10

Max Range: 2.3360. Min Range: -2.3360

Max Act: 2.2187. Min Act: -0.1700

Data Index: 2854190 (Open Web Text)

Max Activating Token Index: 1022

Text #11

Max Range: 2.3360. Min Range: -2.3360

Max Act: 2.2030. Min Act: -0.1700

Data Index: 7273976 (Open Web Text)

Max Activating Token Index: 1022

Text #12

Max Range: 2.3360. Min Range: -2.3360

Max Act: 2.1844. Min Act: -0.1700

Data Index: 1308519 (Open Web Text)

Max Activating Token Index: 1022

Text #13

Max Range: 2.3360. Min Range: -2.3360

Max Act: 2.1981. Min Act: -0.1700

Data Index: 2173417 (Open Web Text)

Max Activating Token Index: 1019

Text #14

Max Range: 2.3360. Min Range: -2.3360

Max Act: 2.2036. Min Act: -0.1700

Data Index: 47269 (Open Web Text)

Max Activating Token Index: 1022

Text #15

Max Range: 2.3360. Min Range: -2.3360

Max Act: 2.2113. Min Act: -0.1700

Data Index: 2932164 (Open Web Text)

Max Activating Token Index: 1022

Text #16

Max Range: 2.3360. Min Range: -2.3360

Max Act: 2.2006. Min Act: -0.1699

Data Index: 2916296 (Open Web Text)

Max Activating Token Index: 1022

Text #17

Max Range: 2.3360. Min Range: -2.3360

Max Act: 2.2066. Min Act: -0.1700

Data Index: 2590166 (Open Web Text)

Max Activating Token Index: 1022

Text #18

Max Range: 2.3360. Min Range: -2.3360

Max Act: 2.2206. Min Act: -0.1700

Data Index: 6367894 (Open Web Text)

Max Activating Token Index: 1021

Text #19

Max Range: 2.3360. Min Range: -2.3360

Max Act: 2.1988. Min Act: -0.1699

Data Index: 379502 (Open Web Text)

Max Activating Token Index: 1022