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

Dataset: Open Web Text

Neuron 2212 in Layer 4

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: 5.4090. Min Range: -5.4090

Max Act: 5.4090. Min Act: -0.1700

Data Index: 8082312 (Open Web Text)

Max Activating Token Index: 995

Text #1

Max Range: 5.4090. Min Range: -5.4090

Max Act: 5.2500. Min Act: -0.1700

Data Index: 3620131 (Open Web Text)

Max Activating Token Index: 781

Text #2

Max Range: 5.4090. Min Range: -5.4090

Max Act: 5.2483. Min Act: -0.1700

Data Index: 2348192 (Open Web Text)

Max Activating Token Index: 906

Text #3

Max Range: 5.4090. Min Range: -5.4090

Max Act: 5.1466. Min Act: -0.1700

Data Index: 3494751 (Open Web Text)

Max Activating Token Index: 1022

Text #4

Max Range: 5.4090. Min Range: -5.4090

Max Act: 5.1506. Min Act: -0.1700

Data Index: 5703431 (Open Web Text)

Max Activating Token Index: 613

Text #5

Max Range: 5.4090. Min Range: -5.4090

Max Act: 5.1686. Min Act: -0.1700

Data Index: 4057752 (Open Web Text)

Max Activating Token Index: 121

Text #6

Max Range: 5.4090. Min Range: -5.4090

Max Act: 5.0851. Min Act: -0.1700

Data Index: 409606 (Open Web Text)

Max Activating Token Index: 1009

Text #7

Max Range: 5.4090. Min Range: -5.4090

Max Act: 5.1234. Min Act: -0.1700

Data Index: 2072678 (Open Web Text)

Max Activating Token Index: 391

Text #8

Max Range: 5.4090. Min Range: -5.4090

Max Act: 5.0958. Min Act: -0.1700

Data Index: 5947410 (Open Web Text)

Max Activating Token Index: 70

Text #9

Max Range: 5.4090. Min Range: -5.4090

Max Act: 5.0709. Min Act: -0.1700

Data Index: 1640414 (Open Web Text)

Max Activating Token Index: 197

Text #10

Max Range: 5.4090. Min Range: -5.4090

Max Act: 5.0873. Min Act: -0.1700

Data Index: 2835737 (Open Web Text)

Max Activating Token Index: 890

Text #11

Max Range: 5.4090. Min Range: -5.4090

Max Act: 5.0588. Min Act: -0.1700

Data Index: 4590714 (Open Web Text)

Max Activating Token Index: 601

Text #12

Max Range: 5.4090. Min Range: -5.4090

Max Act: 5.0552. Min Act: -0.1700

Data Index: 358932 (Open Web Text)

Max Activating Token Index: 209

Text #13

Max Range: 5.4090. Min Range: -5.4090

Max Act: 5.0387. Min Act: -0.1700

Data Index: 3696400 (Open Web Text)

Max Activating Token Index: 824

Text #14

Max Range: 5.4090. Min Range: -5.4090

Max Act: 5.0621. Min Act: -0.1700

Data Index: 2509546 (Open Web Text)

Max Activating Token Index: 225

Text #15

Max Range: 5.4090. Min Range: -5.4090

Max Act: 5.0739. Min Act: -0.1700

Data Index: 4221024 (Open Web Text)

Max Activating Token Index: 775

Text #16

Max Range: 5.4090. Min Range: -5.4090

Max Act: 5.0191. Min Act: -0.1700

Data Index: 2899995 (Open Web Text)

Max Activating Token Index: 289

Text #17

Max Range: 5.4090. Min Range: -5.4090

Max Act: 5.0601. Min Act: -0.1700

Data Index: 3953741 (Open Web Text)

Max Activating Token Index: 307

Text #18

Max Range: 5.4090. Min Range: -5.4090

Max Act: 5.0429. Min Act: -0.1700

Data Index: 8746017 (Open Web Text)

Max Activating Token Index: 671

Text #19

Max Range: 5.4090. Min Range: -5.4090

Max Act: 5.0032. Min Act: -0.1700

Data Index: 2686950 (Open Web Text)

Max Activating Token Index: 146