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

Dataset: Open Web Text

Neuron 231 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: 3.5811. Min Range: -3.5811

Max Act: 3.5811. Min Act: -0.1700

Data Index: 8568791 (Open Web Text)

Max Activating Token Index: 935

Text #1

Max Range: 3.5811. Min Range: -3.5811

Max Act: 3.5470. Min Act: -0.1700

Data Index: 8743180 (Open Web Text)

Max Activating Token Index: 543

Text #2

Max Range: 3.5811. Min Range: -3.5811

Max Act: 3.5617. Min Act: -0.1700

Data Index: 7679256 (Open Web Text)

Max Activating Token Index: 1021

Text #3

Max Range: 3.5811. Min Range: -3.5811

Max Act: 3.4857. Min Act: -0.1700

Data Index: 3193901 (Open Web Text)

Max Activating Token Index: 636

Text #4

Max Range: 3.5811. Min Range: -3.5811

Max Act: 3.4566. Min Act: -0.1700

Data Index: 2498432 (Open Web Text)

Max Activating Token Index: 35

Text #5

Max Range: 3.5811. Min Range: -3.5811

Max Act: 3.4538. Min Act: -0.1700

Data Index: 3085384 (Open Web Text)

Max Activating Token Index: 355

Text #6

Max Range: 3.5811. Min Range: -3.5811

Max Act: 3.4749. Min Act: -0.1700

Data Index: 1977379 (Open Web Text)

Max Activating Token Index: 851

Text #7

Max Range: 3.5811. Min Range: -3.5811

Max Act: 3.4438. Min Act: -0.1700

Data Index: 7881182 (Open Web Text)

Max Activating Token Index: 593

Text #8

Max Range: 3.5811. Min Range: -3.5811

Max Act: 3.4234. Min Act: -0.1700

Data Index: 4328666 (Open Web Text)

Max Activating Token Index: 938

Text #9

Max Range: 3.5811. Min Range: -3.5811

Max Act: 3.4619. Min Act: -0.1700

Data Index: 446248 (Open Web Text)

Max Activating Token Index: 255

Text #10

Max Range: 3.5811. Min Range: -3.5811

Max Act: 3.4410. Min Act: -0.1700

Data Index: 3343845 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.5811. Min Range: -3.5811

Max Act: 3.4737. Min Act: -0.1700

Data Index: 685182 (Open Web Text)

Max Activating Token Index: 490

Text #12

Max Range: 3.5811. Min Range: -3.5811

Max Act: 3.4466. Min Act: -0.1700

Data Index: 7840613 (Open Web Text)

Max Activating Token Index: 924

Text #13

Max Range: 3.5811. Min Range: -3.5811

Max Act: 3.4410. Min Act: -0.1700

Data Index: 4056139 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.5811. Min Range: -3.5811

Max Act: 3.4646. Min Act: -0.1700

Data Index: 7319814 (Open Web Text)

Max Activating Token Index: 305

Text #15

Max Range: 3.5811. Min Range: -3.5811

Max Act: 3.4675. Min Act: -0.1700

Data Index: 7287921 (Open Web Text)

Max Activating Token Index: 553

Text #16

Max Range: 3.5811. Min Range: -3.5811

Max Act: 3.4848. Min Act: -0.1700

Data Index: 5623734 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.5811. Min Range: -3.5811

Max Act: 3.4574. Min Act: -0.1700

Data Index: 5273985 (Open Web Text)

Max Activating Token Index: 204

Text #18

Max Range: 3.5811. Min Range: -3.5811

Max Act: 3.4513. Min Act: -0.1700

Data Index: 4985119 (Open Web Text)

Max Activating Token Index: 197

Text #19

Max Range: 3.5811. Min Range: -3.5811

Max Act: 3.4083. Min Act: -0.1700

Data Index: 80193 (Open Web Text)

Max Activating Token Index: 429