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

Dataset: Open Web Text

Neuron 3032 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: 3.6824. Min Range: -3.6824

Max Act: 3.6824. Min Act: -0.1700

Data Index: 4992241 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 3.6824. Min Range: -3.6824

Max Act: 3.6456. Min Act: -0.1700

Data Index: 2794223 (Open Web Text)

Max Activating Token Index: 98

Text #2

Max Range: 3.6824. Min Range: -3.6824

Max Act: 3.6223. Min Act: -0.1700

Data Index: 1434838 (Open Web Text)

Max Activating Token Index: 48

Text #3

Max Range: 3.6824. Min Range: -3.6824

Max Act: 3.6249. Min Act: -0.1700

Data Index: 5106603 (Open Web Text)

Max Activating Token Index: 10

Text #4

Max Range: 3.6824. Min Range: -3.6824

Max Act: 3.6248. Min Act: -0.1700

Data Index: 1986313 (Open Web Text)

Max Activating Token Index: 423

Text #5

Max Range: 3.6824. Min Range: -3.6824

Max Act: 3.6235. Min Act: -0.1700

Data Index: 7076976 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.6824. Min Range: -3.6824

Max Act: 3.6084. Min Act: -0.1700

Data Index: 4115654 (Open Web Text)

Max Activating Token Index: 679

Text #7

Max Range: 3.6824. Min Range: -3.6824

Max Act: 3.6014. Min Act: -0.1700

Data Index: 1919579 (Open Web Text)

Max Activating Token Index: 26

Text #8

Max Range: 3.6824. Min Range: -3.6824

Max Act: 3.6050. Min Act: -0.1700

Data Index: 5973908 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 3.6824. Min Range: -3.6824

Max Act: 3.6349. Min Act: -0.1700

Data Index: 5183384 (Open Web Text)

Max Activating Token Index: 207

Text #10

Max Range: 3.6824. Min Range: -3.6824

Max Act: 3.5806. Min Act: -0.1700

Data Index: 317790 (Open Web Text)

Max Activating Token Index: 644

Text #11

Max Range: 3.6824. Min Range: -3.6824

Max Act: 3.5756. Min Act: -0.1700

Data Index: 6924189 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.6824. Min Range: -3.6824

Max Act: 3.5917. Min Act: -0.1700

Data Index: 1178541 (Open Web Text)

Max Activating Token Index: 49

Text #13

Max Range: 3.6824. Min Range: -3.6824

Max Act: 3.5764. Min Act: -0.1700

Data Index: 571505 (Open Web Text)

Max Activating Token Index: 307

Text #14

Max Range: 3.6824. Min Range: -3.6824

Max Act: 3.5857. Min Act: -0.1700

Data Index: 4693023 (Open Web Text)

Max Activating Token Index: 522

Text #15

Max Range: 3.6824. Min Range: -3.6824

Max Act: 3.5734. Min Act: -0.1700

Data Index: 8002882 (Open Web Text)

Max Activating Token Index: 681

Text #16

Max Range: 3.6824. Min Range: -3.6824

Max Act: 3.5842. Min Act: -0.1700

Data Index: 8047462 (Open Web Text)

Max Activating Token Index: 310

Text #17

Max Range: 3.6824. Min Range: -3.6824

Max Act: 3.5736. Min Act: -0.1700

Data Index: 2557654 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 3.6824. Min Range: -3.6824

Max Act: 3.5874. Min Act: -0.1700

Data Index: 108088 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.6824. Min Range: -3.6824

Max Act: 3.5591. Min Act: -0.1700

Data Index: 2674916 (Open Web Text)

Max Activating Token Index: 373