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

Dataset: Open Web Text

Neuron 1128 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: 6.5626. Min Range: -6.5626

Max Act: 6.5626. Min Act: -0.1700

Data Index: 7953813 (Open Web Text)

Max Activating Token Index: 703

Text #1

Max Range: 6.5626. Min Range: -6.5626

Max Act: 6.3092. Min Act: -0.1700

Data Index: 7394263 (Open Web Text)

Max Activating Token Index: 364

Text #2

Max Range: 6.5626. Min Range: -6.5626

Max Act: 6.3205. Min Act: -0.1700

Data Index: 6633565 (Open Web Text)

Max Activating Token Index: 604

Text #3

Max Range: 6.5626. Min Range: -6.5626

Max Act: 6.3069. Min Act: -0.1700

Data Index: 2594023 (Open Web Text)

Max Activating Token Index: 679

Text #4

Max Range: 6.5626. Min Range: -6.5626

Max Act: 6.2788. Min Act: -0.1700

Data Index: 4544476 (Open Web Text)

Max Activating Token Index: 213

Text #5

Max Range: 6.5626. Min Range: -6.5626

Max Act: 6.2168. Min Act: -0.1700

Data Index: 1016765 (Open Web Text)

Max Activating Token Index: 823

Text #6

Max Range: 6.5626. Min Range: -6.5626

Max Act: 6.1804. Min Act: -0.1700

Data Index: 3076117 (Open Web Text)

Max Activating Token Index: 1010

Text #7

Max Range: 6.5626. Min Range: -6.5626

Max Act: 6.1578. Min Act: -0.1700

Data Index: 8429199 (Open Web Text)

Max Activating Token Index: 101

Text #8

Max Range: 6.5626. Min Range: -6.5626

Max Act: 6.1877. Min Act: -0.1700

Data Index: 2088940 (Open Web Text)

Max Activating Token Index: 516

Text #9

Max Range: 6.5626. Min Range: -6.5626

Max Act: 6.1098. Min Act: -0.1700

Data Index: 1006124 (Open Web Text)

Max Activating Token Index: 312

Text #10

Max Range: 6.5626. Min Range: -6.5626

Max Act: 6.1407. Min Act: -0.1700

Data Index: 8643473 (Open Web Text)

Max Activating Token Index: 648

Text #11

Max Range: 6.5626. Min Range: -6.5626

Max Act: 6.1103. Min Act: -0.1700

Data Index: 8405908 (Open Web Text)

Max Activating Token Index: 496

Text #12

Max Range: 6.5626. Min Range: -6.5626

Max Act: 6.0697. Min Act: -0.1700

Data Index: 5478393 (Open Web Text)

Max Activating Token Index: 443

Text #13

Max Range: 6.5626. Min Range: -6.5626

Max Act: 6.0925. Min Act: -0.1700

Data Index: 3352749 (Open Web Text)

Max Activating Token Index: 299

Text #14

Max Range: 6.5626. Min Range: -6.5626

Max Act: 6.1240. Min Act: -0.1700

Data Index: 8428988 (Open Web Text)

Max Activating Token Index: 630

Text #15

Max Range: 6.5626. Min Range: -6.5626

Max Act: 6.0790. Min Act: -0.1700

Data Index: 3870502 (Open Web Text)

Max Activating Token Index: 322

Text #16

Max Range: 6.5626. Min Range: -6.5626

Max Act: 6.0719. Min Act: -0.1700

Data Index: 7630799 (Open Web Text)

Max Activating Token Index: 582

Text #17

Max Range: 6.5626. Min Range: -6.5626

Max Act: 6.0332. Min Act: -0.1700

Data Index: 4646762 (Open Web Text)

Max Activating Token Index: 714

Text #18

Max Range: 6.5626. Min Range: -6.5626

Max Act: 6.0211. Min Act: -0.1700

Data Index: 331011 (Open Web Text)

Max Activating Token Index: 779

Text #19

Max Range: 6.5626. Min Range: -6.5626

Max Act: 6.0633. Min Act: -0.1700

Data Index: 3023280 (Open Web Text)

Max Activating Token Index: 994