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

Dataset: Open Web Text

Neuron 1512 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: 5.7815. Min Range: -5.7815

Max Act: 5.7815. Min Act: -0.1700

Data Index: 4243910 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 5.7815. Min Range: -5.7815

Max Act: 5.5292. Min Act: -0.1700

Data Index: 1239188 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 5.7815. Min Range: -5.7815

Max Act: 5.5227. Min Act: -0.1700

Data Index: 7669088 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 5.7815. Min Range: -5.7815

Max Act: 5.5446. Min Act: -0.1700

Data Index: 7165838 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 5.7815. Min Range: -5.7815

Max Act: 5.5538. Min Act: -0.1700

Data Index: 573317 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 5.7815. Min Range: -5.7815

Max Act: 5.5033. Min Act: -0.1700

Data Index: 7164910 (Open Web Text)

Max Activating Token Index: 914

Text #6

Max Range: 5.7815. Min Range: -5.7815

Max Act: 5.4888. Min Act: -0.1700

Data Index: 2340200 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 5.7815. Min Range: -5.7815

Max Act: 5.4568. Min Act: -0.1700

Data Index: 4631633 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 5.7815. Min Range: -5.7815

Max Act: 5.4798. Min Act: -0.1700

Data Index: 4604130 (Open Web Text)

Max Activating Token Index: 18

Text #9

Max Range: 5.7815. Min Range: -5.7815

Max Act: 5.4655. Min Act: -0.1700

Data Index: 4382270 (Open Web Text)

Max Activating Token Index: 945

Text #10

Max Range: 5.7815. Min Range: -5.7815

Max Act: 5.4880. Min Act: -0.1700

Data Index: 8644843 (Open Web Text)

Max Activating Token Index: 983

Text #11

Max Range: 5.7815. Min Range: -5.7815

Max Act: 5.4746. Min Act: -0.1700

Data Index: 2373875 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 5.7815. Min Range: -5.7815

Max Act: 5.4599. Min Act: -0.1700

Data Index: 5368337 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 5.7815. Min Range: -5.7815

Max Act: 5.4635. Min Act: -0.1700

Data Index: 886949 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 5.7815. Min Range: -5.7815

Max Act: 5.4843. Min Act: -0.1700

Data Index: 4302007 (Open Web Text)

Max Activating Token Index: 1001

Text #15

Max Range: 5.7815. Min Range: -5.7815

Max Act: 5.4748. Min Act: -0.1700

Data Index: 2989515 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 5.7815. Min Range: -5.7815

Max Act: 5.4578. Min Act: -0.1700

Data Index: 2921929 (Open Web Text)

Max Activating Token Index: 1021

Text #17

Max Range: 5.7815. Min Range: -5.7815

Max Act: 5.4551. Min Act: -0.1700

Data Index: 6268424 (Open Web Text)

Max Activating Token Index: 89

Text #18

Max Range: 5.7815. Min Range: -5.7815

Max Act: 5.4793. Min Act: -0.1700

Data Index: 5496990 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 5.7815. Min Range: -5.7815

Max Act: 5.4384. Min Act: -0.1700

Data Index: 372957 (Open Web Text)

Max Activating Token Index: 912