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

Dataset: Open Web Text

Neuron 987 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: 4.1585. Min Range: -4.1585

Max Act: 4.1585. Min Act: -0.1700

Data Index: 7802089 (Open Web Text)

Max Activating Token Index: 1020

Text #1

Max Range: 4.1585. Min Range: -4.1585

Max Act: 4.1312. Min Act: -0.1700

Data Index: 3931100 (Open Web Text)

Max Activating Token Index: 12

Text #2

Max Range: 4.1585. Min Range: -4.1585

Max Act: 4.0912. Min Act: -0.1700

Data Index: 1387413 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 4.1585. Min Range: -4.1585

Max Act: 4.1015. Min Act: -0.1700

Data Index: 5302491 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 4.1585. Min Range: -4.1585

Max Act: 4.0962. Min Act: -0.1700

Data Index: 3817854 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 4.1585. Min Range: -4.1585

Max Act: 4.1026. Min Act: -0.1700

Data Index: 4522108 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 4.1585. Min Range: -4.1585

Max Act: 4.1038. Min Act: -0.1700

Data Index: 7411738 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 4.1585. Min Range: -4.1585

Max Act: 4.0997. Min Act: -0.1700

Data Index: 3299285 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 4.1585. Min Range: -4.1585

Max Act: 4.1087. Min Act: -0.1700

Data Index: 8778211 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 4.1585. Min Range: -4.1585

Max Act: 4.0929. Min Act: -0.1700

Data Index: 4188998 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 4.1585. Min Range: -4.1585

Max Act: 4.0957. Min Act: -0.1700

Data Index: 8345565 (Open Web Text)

Max Activating Token Index: 17

Text #11

Max Range: 4.1585. Min Range: -4.1585

Max Act: 4.0775. Min Act: -0.1700

Data Index: 5922645 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 4.1585. Min Range: -4.1585

Max Act: 4.0792. Min Act: -0.1700

Data Index: 4404283 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 4.1585. Min Range: -4.1585

Max Act: 4.0707. Min Act: -0.1700

Data Index: 4390024 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 4.1585. Min Range: -4.1585

Max Act: 4.0655. Min Act: -0.1700

Data Index: 4256535 (Open Web Text)

Max Activating Token Index: 988

Text #15

Max Range: 4.1585. Min Range: -4.1585

Max Act: 4.0763. Min Act: -0.1700

Data Index: 5169697 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 4.1585. Min Range: -4.1585

Max Act: 4.0638. Min Act: -0.1700

Data Index: 7915221 (Open Web Text)

Max Activating Token Index: 9

Text #17

Max Range: 4.1585. Min Range: -4.1585

Max Act: 4.0695. Min Act: -0.1700

Data Index: 5502367 (Open Web Text)

Max Activating Token Index: 1020

Text #18

Max Range: 4.1585. Min Range: -4.1585

Max Act: 4.0369. Min Act: -0.1700

Data Index: 6746679 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 4.1585. Min Range: -4.1585

Max Act: 4.0586. Min Act: -0.1700

Data Index: 2589382 (Open Web Text)

Max Activating Token Index: 11