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

Dataset: Open Web Text

Neuron 2279 in Layer 3

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: 3.9378. Min Range: -3.9378

Max Act: 3.9173. Min Act: -0.1700

Data Index: 3266896 (Open Web Text)

Max Activating Token Index: 581

Text #1

Max Range: 3.9378. Min Range: -3.9378

Max Act: 3.9266. Min Act: -0.1700

Data Index: 7984476 (Open Web Text)

Max Activating Token Index: 567

Text #2

Max Range: 3.9378. Min Range: -3.9378

Max Act: 3.9378. Min Act: -0.1700

Data Index: 6501033 (Open Web Text)

Max Activating Token Index: 354

Text #3

Max Range: 3.9378. Min Range: -3.9378

Max Act: 3.9142. Min Act: -0.1700

Data Index: 2261154 (Open Web Text)

Max Activating Token Index: 364

Text #4

Max Range: 3.9378. Min Range: -3.9378

Max Act: 3.8724. Min Act: -0.1700

Data Index: 5587393 (Open Web Text)

Max Activating Token Index: 713

Text #5

Max Range: 3.9378. Min Range: -3.9378

Max Act: 3.9099. Min Act: -0.1700

Data Index: 4075915 (Open Web Text)

Max Activating Token Index: 1022

Text #6

Max Range: 3.9378. Min Range: -3.9378

Max Act: 3.8868. Min Act: -0.1700

Data Index: 5622549 (Open Web Text)

Max Activating Token Index: 288

Text #7

Max Range: 3.9378. Min Range: -3.9378

Max Act: 3.8834. Min Act: -0.1700

Data Index: 7055877 (Open Web Text)

Max Activating Token Index: 193

Text #8

Max Range: 3.9378. Min Range: -3.9378

Max Act: 3.8954. Min Act: -0.1699

Data Index: 640793 (Open Web Text)

Max Activating Token Index: 140

Text #9

Max Range: 3.9378. Min Range: -3.9378

Max Act: 3.8590. Min Act: -0.1700

Data Index: 3604127 (Open Web Text)

Max Activating Token Index: 708

Text #10

Max Range: 3.9378. Min Range: -3.9378

Max Act: 3.8486. Min Act: -0.1700

Data Index: 5784023 (Open Web Text)

Max Activating Token Index: 78

Text #11

Max Range: 3.9378. Min Range: -3.9378

Max Act: 3.8437. Min Act: -0.1700

Data Index: 848723 (Open Web Text)

Max Activating Token Index: 125

Text #12

Max Range: 3.9378. Min Range: -3.9378

Max Act: 3.9031. Min Act: -0.1700

Data Index: 8503890 (Open Web Text)

Max Activating Token Index: 847

Text #13

Max Range: 3.9378. Min Range: -3.9378

Max Act: 3.8488. Min Act: -0.1700

Data Index: 3607462 (Open Web Text)

Max Activating Token Index: 374

Text #14

Max Range: 3.9378. Min Range: -3.9378

Max Act: 3.8024. Min Act: -0.1700

Data Index: 5341783 (Open Web Text)

Max Activating Token Index: 789

Text #15

Max Range: 3.9378. Min Range: -3.9378

Max Act: 3.8256. Min Act: -0.1700

Data Index: 5651315 (Open Web Text)

Max Activating Token Index: 285

Text #16

Max Range: 3.9378. Min Range: -3.9378

Max Act: 3.8341. Min Act: -0.1700

Data Index: 2023064 (Open Web Text)

Max Activating Token Index: 616

Text #17

Max Range: 3.9378. Min Range: -3.9378

Max Act: 3.7918. Min Act: -0.1700

Data Index: 2861167 (Open Web Text)

Max Activating Token Index: 634

Text #18

Max Range: 3.9378. Min Range: -3.9378

Max Act: 3.7745. Min Act: -0.1700

Data Index: 6682878 (Open Web Text)

Max Activating Token Index: 579

Text #19

Max Range: 3.9378. Min Range: -3.9378

Max Act: 3.7726. Min Act: -0.1700

Data Index: 946143 (Open Web Text)

Max Activating Token Index: 556