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

Dataset: Open Web Text

Neuron 2821 in Layer 4

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: 2.0995. Min Range: -2.0995

Max Act: 2.0982. Min Act: -0.1700

Data Index: 1177432 (Open Web Text)

Max Activating Token Index: 40

Text #1

Max Range: 2.0995. Min Range: -2.0995

Max Act: 2.0871. Min Act: -0.1700

Data Index: 7447832 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 2.0995. Min Range: -2.0995

Max Act: 2.0995. Min Act: -0.1700

Data Index: 2405337 (Open Web Text)

Max Activating Token Index: 34

Text #3

Max Range: 2.0995. Min Range: -2.0995

Max Act: 2.0507. Min Act: -0.1700

Data Index: 2164299 (Open Web Text)

Max Activating Token Index: 57

Text #4

Max Range: 2.0995. Min Range: -2.0995

Max Act: 2.0200. Min Act: -0.1700

Data Index: 4046217 (Open Web Text)

Max Activating Token Index: 18

Text #5

Max Range: 2.0995. Min Range: -2.0995

Max Act: 2.0321. Min Act: -0.1700

Data Index: 5234519 (Open Web Text)

Max Activating Token Index: 11

Text #6

Max Range: 2.0995. Min Range: -2.0995

Max Act: 1.9830. Min Act: -0.1700

Data Index: 7003445 (Open Web Text)

Max Activating Token Index: 487

Text #7

Max Range: 2.0995. Min Range: -2.0995

Max Act: 1.9696. Min Act: -0.1700

Data Index: 4313252 (Open Web Text)

Max Activating Token Index: 20

Text #8

Max Range: 2.0995. Min Range: -2.0995

Max Act: 1.9562. Min Act: -0.1700

Data Index: 2525660 (Open Web Text)

Max Activating Token Index: 19

Text #9

Max Range: 2.0995. Min Range: -2.0995

Max Act: 1.9489. Min Act: -0.1700

Data Index: 402686 (Open Web Text)

Max Activating Token Index: 885

Text #10

Max Range: 2.0995. Min Range: -2.0995

Max Act: 1.9476. Min Act: -0.1700

Data Index: 8050644 (Open Web Text)

Max Activating Token Index: 22

Text #11

Max Range: 2.0995. Min Range: -2.0995

Max Act: 1.9098. Min Act: -0.1700

Data Index: 8050643 (Open Web Text)

Max Activating Token Index: 508

Text #12

Max Range: 2.0995. Min Range: -2.0995

Max Act: 1.9328. Min Act: -0.1700

Data Index: 4086775 (Open Web Text)

Max Activating Token Index: 12

Text #13

Max Range: 2.0995. Min Range: -2.0995

Max Act: 1.9235. Min Act: -0.1700

Data Index: 7434897 (Open Web Text)

Max Activating Token Index: 36

Text #14

Max Range: 2.0995. Min Range: -2.0995

Max Act: 1.8950. Min Act: -0.1700

Data Index: 229155 (Open Web Text)

Max Activating Token Index: 163

Text #15

Max Range: 2.0995. Min Range: -2.0995

Max Act: 1.8923. Min Act: -0.1700

Data Index: 2416025 (Open Web Text)

Max Activating Token Index: 26

Text #16

Max Range: 2.0995. Min Range: -2.0995

Max Act: 1.8830. Min Act: -0.1700

Data Index: 7587912 (Open Web Text)

Max Activating Token Index: 303

Text #17

Max Range: 2.0995. Min Range: -2.0995

Max Act: 1.9103. Min Act: -0.1700

Data Index: 7046796 (Open Web Text)

Max Activating Token Index: 22

Text #18

Max Range: 2.0995. Min Range: -2.0995

Max Act: 1.8990. Min Act: -0.1700

Data Index: 2902434 (Open Web Text)

Max Activating Token Index: 27

Text #19

Max Range: 2.0995. Min Range: -2.0995

Max Act: 1.8960. Min Act: -0.1700

Data Index: 960616 (Open Web Text)

Max Activating Token Index: 5