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

Dataset: Open Web Text

Neuron 253 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: 4.8013. Min Range: -4.8013

Max Act: 4.8013. Min Act: -0.1700

Data Index: 190671 (Open Web Text)

Max Activating Token Index: 528

Text #1

Max Range: 4.8013. Min Range: -4.8013

Max Act: 4.7501. Min Act: -0.1700

Data Index: 2591746 (Open Web Text)

Max Activating Token Index: 401

Text #2

Max Range: 4.8013. Min Range: -4.8013

Max Act: 4.7407. Min Act: -0.1700

Data Index: 283386 (Open Web Text)

Max Activating Token Index: 558

Text #3

Max Range: 4.8013. Min Range: -4.8013

Max Act: 4.7451. Min Act: -0.1700

Data Index: 1501997 (Open Web Text)

Max Activating Token Index: 498

Text #4

Max Range: 4.8013. Min Range: -4.8013

Max Act: 4.7500. Min Act: -0.1700

Data Index: 1562992 (Open Web Text)

Max Activating Token Index: 591

Text #5

Max Range: 4.8013. Min Range: -4.8013

Max Act: 4.6821. Min Act: -0.1700

Data Index: 8641341 (Open Web Text)

Max Activating Token Index: 344

Text #6

Max Range: 4.8013. Min Range: -4.8013

Max Act: 4.6912. Min Act: -0.1699

Data Index: 119971 (Open Web Text)

Max Activating Token Index: 1005

Text #7

Max Range: 4.8013. Min Range: -4.8013

Max Act: 4.6965. Min Act: -0.1700

Data Index: 6057386 (Open Web Text)

Max Activating Token Index: 806

Text #8

Max Range: 4.8013. Min Range: -4.8013

Max Act: 4.6828. Min Act: -0.1700

Data Index: 5860263 (Open Web Text)

Max Activating Token Index: 528

Text #9

Max Range: 4.8013. Min Range: -4.8013

Max Act: 4.6949. Min Act: -0.1700

Data Index: 4094540 (Open Web Text)

Max Activating Token Index: 816

Text #10

Max Range: 4.8013. Min Range: -4.8013

Max Act: 4.6894. Min Act: -0.1700

Data Index: 1489049 (Open Web Text)

Max Activating Token Index: 625

Text #11

Max Range: 4.8013. Min Range: -4.8013

Max Act: 4.7078. Min Act: -0.1700

Data Index: 889169 (Open Web Text)

Max Activating Token Index: 330

Text #12

Max Range: 4.8013. Min Range: -4.8013

Max Act: 4.6727. Min Act: -0.1700

Data Index: 7664309 (Open Web Text)

Max Activating Token Index: 804

Text #13

Max Range: 4.8013. Min Range: -4.8013

Max Act: 4.6446. Min Act: -0.1700

Data Index: 963838 (Open Web Text)

Max Activating Token Index: 422

Text #14

Max Range: 4.8013. Min Range: -4.8013

Max Act: 4.6439. Min Act: -0.1700

Data Index: 2954100 (Open Web Text)

Max Activating Token Index: 400

Text #15

Max Range: 4.8013. Min Range: -4.8013

Max Act: 4.6758. Min Act: -0.1700

Data Index: 2959455 (Open Web Text)

Max Activating Token Index: 18

Text #16

Max Range: 4.8013. Min Range: -4.8013

Max Act: 4.6585. Min Act: -0.1700

Data Index: 1162778 (Open Web Text)

Max Activating Token Index: 485

Text #17

Max Range: 4.8013. Min Range: -4.8013

Max Act: 4.6654. Min Act: -0.1700

Data Index: 188123 (Open Web Text)

Max Activating Token Index: 665

Text #18

Max Range: 4.8013. Min Range: -4.8013

Max Act: 4.6738. Min Act: -0.1700

Data Index: 7205274 (Open Web Text)

Max Activating Token Index: 429

Text #19

Max Range: 4.8013. Min Range: -4.8013

Max Act: 4.6544. Min Act: -0.1700

Data Index: 3321282 (Open Web Text)

Max Activating Token Index: 230