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

Dataset: Open Web Text

Neuron 364 in Layer 5

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: 3.7036. Min Range: -3.7036

Max Act: 3.7036. Min Act: -0.1700

Data Index: 3136685 (Open Web Text)

Max Activating Token Index: 771

Text #1

Max Range: 3.7036. Min Range: -3.7036

Max Act: 3.5916. Min Act: -0.1700

Data Index: 7448163 (Open Web Text)

Max Activating Token Index: 576

Text #2

Max Range: 3.7036. Min Range: -3.7036

Max Act: 3.5292. Min Act: -0.1700

Data Index: 2446777 (Open Web Text)

Max Activating Token Index: 605

Text #3

Max Range: 3.7036. Min Range: -3.7036

Max Act: 3.5283. Min Act: -0.1700

Data Index: 3668571 (Open Web Text)

Max Activating Token Index: 383

Text #4

Max Range: 3.7036. Min Range: -3.7036

Max Act: 3.5194. Min Act: -0.1700

Data Index: 2369525 (Open Web Text)

Max Activating Token Index: 849

Text #5

Max Range: 3.7036. Min Range: -3.7036

Max Act: 3.5200. Min Act: -0.1700

Data Index: 3516024 (Open Web Text)

Max Activating Token Index: 718

Text #6

Max Range: 3.7036. Min Range: -3.7036

Max Act: 3.5073. Min Act: -0.1700

Data Index: 3925682 (Open Web Text)

Max Activating Token Index: 257

Text #7

Max Range: 3.7036. Min Range: -3.7036

Max Act: 3.4927. Min Act: -0.1700

Data Index: 6785324 (Open Web Text)

Max Activating Token Index: 321

Text #8

Max Range: 3.7036. Min Range: -3.7036

Max Act: 3.4761. Min Act: -0.1700

Data Index: 8557570 (Open Web Text)

Max Activating Token Index: 570

Text #9

Max Range: 3.7036. Min Range: -3.7036

Max Act: 3.4689. Min Act: -0.1700

Data Index: 7487378 (Open Web Text)

Max Activating Token Index: 228

Text #10

Max Range: 3.7036. Min Range: -3.7036

Max Act: 3.4433. Min Act: -0.1700

Data Index: 5844658 (Open Web Text)

Max Activating Token Index: 796

Text #11

Max Range: 3.7036. Min Range: -3.7036

Max Act: 3.4383. Min Act: -0.1700

Data Index: 8301361 (Open Web Text)

Max Activating Token Index: 853

Text #12

Max Range: 3.7036. Min Range: -3.7036

Max Act: 3.4314. Min Act: -0.1700

Data Index: 8435425 (Open Web Text)

Max Activating Token Index: 556

Text #13

Max Range: 3.7036. Min Range: -3.7036

Max Act: 3.4318. Min Act: -0.1700

Data Index: 3749322 (Open Web Text)

Max Activating Token Index: 582

Text #14

Max Range: 3.7036. Min Range: -3.7036

Max Act: 3.4154. Min Act: -0.1700

Data Index: 4570738 (Open Web Text)

Max Activating Token Index: 960

Text #15

Max Range: 3.7036. Min Range: -3.7036

Max Act: 3.4128. Min Act: -0.1700

Data Index: 6985872 (Open Web Text)

Max Activating Token Index: 884

Text #16

Max Range: 3.7036. Min Range: -3.7036

Max Act: 3.4043. Min Act: -0.1700

Data Index: 5093279 (Open Web Text)

Max Activating Token Index: 811

Text #17

Max Range: 3.7036. Min Range: -3.7036

Max Act: 3.4126. Min Act: -0.1700

Data Index: 523574 (Open Web Text)

Max Activating Token Index: 194

Text #18

Max Range: 3.7036. Min Range: -3.7036

Max Act: 3.3969. Min Act: -0.1700

Data Index: 1421200 (Open Web Text)

Max Activating Token Index: 227

Text #19

Max Range: 3.7036. Min Range: -3.7036

Max Act: 3.3905. Min Act: -0.1700

Data Index: 2710897 (Open Web Text)

Max Activating Token Index: 726