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

Dataset: Open Web Text

Neuron 1100 in Layer 2

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: 4.1502. Min Range: -4.1502

Max Act: 4.1502. Min Act: -0.1700

Data Index: 5446674 (Open Web Text)

Max Activating Token Index: 283

Text #1

Max Range: 4.1502. Min Range: -4.1502

Max Act: 4.1097. Min Act: -0.1700

Data Index: 5604063 (Open Web Text)

Max Activating Token Index: 704

Text #2

Max Range: 4.1502. Min Range: -4.1502

Max Act: 4.1341. Min Act: -0.1700

Data Index: 5604054 (Open Web Text)

Max Activating Token Index: 531

Text #3

Max Range: 4.1502. Min Range: -4.1502

Max Act: 4.0925. Min Act: -0.1700

Data Index: 1815455 (Open Web Text)

Max Activating Token Index: 541

Text #4

Max Range: 4.1502. Min Range: -4.1502

Max Act: 4.1168. Min Act: -0.1700

Data Index: 4531695 (Open Web Text)

Max Activating Token Index: 131

Text #5

Max Range: 4.1502. Min Range: -4.1502

Max Act: 4.1280. Min Act: -0.1700

Data Index: 4031750 (Open Web Text)

Max Activating Token Index: 230

Text #6

Max Range: 4.1502. Min Range: -4.1502

Max Act: 4.0617. Min Act: -0.1700

Data Index: 2051024 (Open Web Text)

Max Activating Token Index: 294

Text #7

Max Range: 4.1502. Min Range: -4.1502

Max Act: 4.0561. Min Act: -0.1700

Data Index: 4983590 (Open Web Text)

Max Activating Token Index: 762

Text #8

Max Range: 4.1502. Min Range: -4.1502

Max Act: 4.0807. Min Act: -0.1700

Data Index: 5985179 (Open Web Text)

Max Activating Token Index: 460

Text #9

Max Range: 4.1502. Min Range: -4.1502

Max Act: 4.0012. Min Act: -0.1700

Data Index: 1731047 (Open Web Text)

Max Activating Token Index: 737

Text #10

Max Range: 4.1502. Min Range: -4.1502

Max Act: 4.0144. Min Act: -0.1700

Data Index: 3076258 (Open Web Text)

Max Activating Token Index: 349

Text #11

Max Range: 4.1502. Min Range: -4.1502

Max Act: 4.0292. Min Act: -0.1700

Data Index: 6127324 (Open Web Text)

Max Activating Token Index: 694

Text #12

Max Range: 4.1502. Min Range: -4.1502

Max Act: 4.0138. Min Act: -0.1700

Data Index: 5984579 (Open Web Text)

Max Activating Token Index: 36

Text #13

Max Range: 4.1502. Min Range: -4.1502

Max Act: 3.9966. Min Act: -0.1700

Data Index: 512248 (Open Web Text)

Max Activating Token Index: 683

Text #14

Max Range: 4.1502. Min Range: -4.1502

Max Act: 4.0019. Min Act: -0.1700

Data Index: 73428 (Open Web Text)

Max Activating Token Index: 763

Text #15

Max Range: 4.1502. Min Range: -4.1502

Max Act: 3.9906. Min Act: -0.1700

Data Index: 2542650 (Open Web Text)

Max Activating Token Index: 280

Text #16

Max Range: 4.1502. Min Range: -4.1502

Max Act: 3.9954. Min Act: -0.1700

Data Index: 3923604 (Open Web Text)

Max Activating Token Index: 213

Text #17

Max Range: 4.1502. Min Range: -4.1502

Max Act: 3.9915. Min Act: -0.1700

Data Index: 1731046 (Open Web Text)

Max Activating Token Index: 591

Text #18

Max Range: 4.1502. Min Range: -4.1502

Max Act: 3.9418. Min Act: -0.1700

Data Index: 5242292 (Open Web Text)

Max Activating Token Index: 451

Text #19

Max Range: 4.1502. Min Range: -4.1502

Max Act: 3.9864. Min Act: -0.1700

Data Index: 1434188 (Open Web Text)

Max Activating Token Index: 752