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

Dataset: Open Web Text

Neuron 777 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: 5.0623. Min Range: -5.0623

Max Act: 5.0623. Min Act: -0.1700

Data Index: 4910186 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 5.0623. Min Range: -5.0623

Max Act: 4.9873. Min Act: -0.1700

Data Index: 4808918 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 5.0623. Min Range: -5.0623

Max Act: 4.9797. Min Act: -0.1700

Data Index: 2517208 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 5.0623. Min Range: -5.0623

Max Act: 4.9748. Min Act: -0.1700

Data Index: 1175315 (Open Web Text)

Max Activating Token Index: 10

Text #4

Max Range: 5.0623. Min Range: -5.0623

Max Act: 4.9542. Min Act: -0.1700

Data Index: 2127571 (Open Web Text)

Max Activating Token Index: 64

Text #5

Max Range: 5.0623. Min Range: -5.0623

Max Act: 4.9694. Min Act: -0.1700

Data Index: 8085637 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 5.0623. Min Range: -5.0623

Max Act: 4.9312. Min Act: -0.1700

Data Index: 4137530 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 5.0623. Min Range: -5.0623

Max Act: 4.9395. Min Act: -0.1700

Data Index: 2538788 (Open Web Text)

Max Activating Token Index: 9

Text #8

Max Range: 5.0623. Min Range: -5.0623

Max Act: 4.9337. Min Act: -0.1700

Data Index: 637773 (Open Web Text)

Max Activating Token Index: 11

Text #9

Max Range: 5.0623. Min Range: -5.0623

Max Act: 4.9259. Min Act: -0.1700

Data Index: 2578902 (Open Web Text)

Max Activating Token Index: 354

Text #10

Max Range: 5.0623. Min Range: -5.0623

Max Act: 4.9342. Min Act: -0.1700

Data Index: 1068784 (Open Web Text)

Max Activating Token Index: 19

Text #11

Max Range: 5.0623. Min Range: -5.0623

Max Act: 4.9288. Min Act: -0.1700

Data Index: 7340814 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 5.0623. Min Range: -5.0623

Max Act: 4.9273. Min Act: -0.1700

Data Index: 4128700 (Open Web Text)

Max Activating Token Index: 14

Text #13

Max Range: 5.0623. Min Range: -5.0623

Max Act: 4.9428. Min Act: -0.1700

Data Index: 7330867 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 5.0623. Min Range: -5.0623

Max Act: 4.9204. Min Act: -0.1700

Data Index: 5289359 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 5.0623. Min Range: -5.0623

Max Act: 4.9377. Min Act: -0.1700

Data Index: 769480 (Open Web Text)

Max Activating Token Index: 9

Text #16

Max Range: 5.0623. Min Range: -5.0623

Max Act: 4.8822. Min Act: -0.1700

Data Index: 2676320 (Open Web Text)

Max Activating Token Index: 13

Text #17

Max Range: 5.0623. Min Range: -5.0623

Max Act: 4.9070. Min Act: -0.1700

Data Index: 4831196 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 5.0623. Min Range: -5.0623

Max Act: 4.8867. Min Act: -0.1700

Data Index: 1166987 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 5.0623. Min Range: -5.0623

Max Act: 4.8983. Min Act: -0.1700

Data Index: 4784009 (Open Web Text)

Max Activating Token Index: 16