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

Dataset: Open Web Text

Neuron 217 in Layer 0

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: 2.8247. Min Range: -2.8247

Max Act: 2.8247. Min Act: -0.1700

Data Index: 3537966 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 2.8247. Min Range: -2.8247

Max Act: 2.8002. Min Act: -0.1700

Data Index: 2017150 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 2.8247. Min Range: -2.8247

Max Act: 2.8002. Min Act: -0.1700

Data Index: 1371080 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 2.8247. Min Range: -2.8247

Max Act: 2.7869. Min Act: -0.1700

Data Index: 5433334 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 2.8247. Min Range: -2.8247

Max Act: 2.7869. Min Act: -0.1700

Data Index: 7698265 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 2.8247. Min Range: -2.8247

Max Act: 2.7678. Min Act: -0.1700

Data Index: 3702604 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 2.8247. Min Range: -2.8247

Max Act: 2.7759. Min Act: -0.1700

Data Index: 3016837 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 2.8247. Min Range: -2.8247

Max Act: 2.7584. Min Act: -0.1700

Data Index: 6238880 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 2.8247. Min Range: -2.8247

Max Act: 2.7574. Min Act: -0.1700

Data Index: 2671794 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 2.8247. Min Range: -2.8247

Max Act: 2.7574. Min Act: -0.1700

Data Index: 8728810 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 2.8247. Min Range: -2.8247

Max Act: 2.7209. Min Act: -0.1700

Data Index: 1393864 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 2.8247. Min Range: -2.8247

Max Act: 2.7090. Min Act: -0.1700

Data Index: 5301782 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 2.8247. Min Range: -2.8247

Max Act: 2.6961. Min Act: -0.1700

Data Index: 2201754 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 2.8247. Min Range: -2.8247

Max Act: 2.6974. Min Act: -0.1700

Data Index: 4373878 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 2.8247. Min Range: -2.8247

Max Act: 2.6921. Min Act: -0.1700

Data Index: 1922311 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 2.8247. Min Range: -2.8247

Max Act: 2.6848. Min Act: -0.1700

Data Index: 3186864 (Open Web Text)

Max Activating Token Index: 22

Text #16

Max Range: 2.8247. Min Range: -2.8247

Max Act: 2.6744. Min Act: -0.1700

Data Index: 4088949 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 2.8247. Min Range: -2.8247

Max Act: 2.6807. Min Act: -0.1700

Data Index: 3936628 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 2.8247. Min Range: -2.8247

Max Act: 2.6741. Min Act: -0.1700

Data Index: 6040781 (Open Web Text)

Max Activating Token Index: 15

Text #19

Max Range: 2.8247. Min Range: -2.8247

Max Act: 2.6535. Min Act: -0.1700

Data Index: 6154745 (Open Web Text)

Max Activating Token Index: 409