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

Dataset: Open Web Text

Neuron 678 in Layer 6

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: 4.4910. Min Range: -4.4910

Max Act: 4.4778. Min Act: -0.1700

Data Index: 728336 (Open Web Text)

Max Activating Token Index: 457

Text #1

Max Range: 4.4910. Min Range: -4.4910

Max Act: 4.4910. Min Act: -0.1700

Data Index: 8031579 (Open Web Text)

Max Activating Token Index: 832

Text #2

Max Range: 4.4910. Min Range: -4.4910

Max Act: 4.4108. Min Act: -0.1700

Data Index: 1236169 (Open Web Text)

Max Activating Token Index: 403

Text #3

Max Range: 4.4910. Min Range: -4.4910

Max Act: 4.4509. Min Act: -0.1700

Data Index: 307457 (Open Web Text)

Max Activating Token Index: 78

Text #4

Max Range: 4.4910. Min Range: -4.4910

Max Act: 4.4152. Min Act: -0.1700

Data Index: 4267609 (Open Web Text)

Max Activating Token Index: 932

Text #5

Max Range: 4.4910. Min Range: -4.4910

Max Act: 4.3976. Min Act: -0.1700

Data Index: 5814555 (Open Web Text)

Max Activating Token Index: 692

Text #6

Max Range: 4.4910. Min Range: -4.4910

Max Act: 4.3622. Min Act: -0.1700

Data Index: 8031570 (Open Web Text)

Max Activating Token Index: 264

Text #7

Max Range: 4.4910. Min Range: -4.4910

Max Act: 4.3737. Min Act: -0.1700

Data Index: 8031571 (Open Web Text)

Max Activating Token Index: 444

Text #8

Max Range: 4.4910. Min Range: -4.4910

Max Act: 4.3584. Min Act: -0.1700

Data Index: 5373799 (Open Web Text)

Max Activating Token Index: 837

Text #9

Max Range: 4.4910. Min Range: -4.4910

Max Act: 4.3499. Min Act: -0.1700

Data Index: 1912427 (Open Web Text)

Max Activating Token Index: 70

Text #10

Max Range: 4.4910. Min Range: -4.4910

Max Act: 4.3758. Min Act: -0.1700

Data Index: 8031568 (Open Web Text)

Max Activating Token Index: 165

Text #11

Max Range: 4.4910. Min Range: -4.4910

Max Act: 4.3292. Min Act: -0.1700

Data Index: 5417033 (Open Web Text)

Max Activating Token Index: 866

Text #12

Max Range: 4.4910. Min Range: -4.4910

Max Act: 4.2861. Min Act: -0.1700

Data Index: 615296 (Open Web Text)

Max Activating Token Index: 923

Text #13

Max Range: 4.4910. Min Range: -4.4910

Max Act: 4.3679. Min Act: -0.1700

Data Index: 8031584 (Open Web Text)

Max Activating Token Index: 305

Text #14

Max Range: 4.4910. Min Range: -4.4910

Max Act: 4.3120. Min Act: -0.1700

Data Index: 3841589 (Open Web Text)

Max Activating Token Index: 928

Text #15

Max Range: 4.4910. Min Range: -4.4910

Max Act: 4.3231. Min Act: -0.1700

Data Index: 8031565 (Open Web Text)

Max Activating Token Index: 340

Text #16

Max Range: 4.4910. Min Range: -4.4910

Max Act: 4.2702. Min Act: -0.1700

Data Index: 3344774 (Open Web Text)

Max Activating Token Index: 488

Text #17

Max Range: 4.4910. Min Range: -4.4910

Max Act: 4.2544. Min Act: -0.1700

Data Index: 137518 (Open Web Text)

Max Activating Token Index: 369

Text #18

Max Range: 4.4910. Min Range: -4.4910

Max Act: 4.3017. Min Act: -0.1700

Data Index: 3304683 (Open Web Text)

Max Activating Token Index: 745

Text #19

Max Range: 4.4910. Min Range: -4.4910

Max Act: 4.3003. Min Act: -0.1700

Data Index: 5269344 (Open Web Text)

Max Activating Token Index: 825