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

Dataset: Open Web Text

Neuron 780 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: 3.8108. Min Range: -3.8108

Max Act: 3.8108. Min Act: -0.1700

Data Index: 4629233 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.8108. Min Range: -3.8108

Max Act: 3.7689. Min Act: -0.1700

Data Index: 1216273 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 3.8108. Min Range: -3.8108

Max Act: 3.7237. Min Act: -0.1700

Data Index: 5680025 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.8108. Min Range: -3.8108

Max Act: 3.7246. Min Act: -0.1700

Data Index: 2518508 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.8108. Min Range: -3.8108

Max Act: 3.7295. Min Act: -0.1700

Data Index: 4764940 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 3.8108. Min Range: -3.8108

Max Act: 3.7302. Min Act: -0.1700

Data Index: 2026983 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.8108. Min Range: -3.8108

Max Act: 3.7237. Min Act: -0.1700

Data Index: 8779746 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.8108. Min Range: -3.8108

Max Act: 3.7237. Min Act: -0.1700

Data Index: 1489982 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.8108. Min Range: -3.8108

Max Act: 3.7159. Min Act: -0.1700

Data Index: 3126659 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 3.8108. Min Range: -3.8108

Max Act: 3.7157. Min Act: -0.1700

Data Index: 3087167 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 3.8108. Min Range: -3.8108

Max Act: 3.7242. Min Act: -0.1700

Data Index: 3072876 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 3.8108. Min Range: -3.8108

Max Act: 3.7237. Min Act: -0.1700

Data Index: 5874181 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.8108. Min Range: -3.8108

Max Act: 3.7237. Min Act: -0.1700

Data Index: 2822663 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.8108. Min Range: -3.8108

Max Act: 3.6729. Min Act: -0.1700

Data Index: 8105473 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.8108. Min Range: -3.8108

Max Act: 3.6973. Min Act: -0.1700

Data Index: 27934 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 3.8108. Min Range: -3.8108

Max Act: 3.7025. Min Act: -0.1700

Data Index: 8006063 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.8108. Min Range: -3.8108

Max Act: 3.6812. Min Act: -0.1700

Data Index: 4263204 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 3.8108. Min Range: -3.8108

Max Act: 3.6811. Min Act: -0.1700

Data Index: 7936538 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.8108. Min Range: -3.8108

Max Act: 3.6454. Min Act: -0.1700

Data Index: 4636973 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 3.8108. Min Range: -3.8108

Max Act: 3.6613. Min Act: -0.1700

Data Index: 2814954 (Open Web Text)

Max Activating Token Index: 841