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

Dataset: Open Web Text

Neuron 2350 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: 3.3707. Min Range: -3.3707

Max Act: 3.3707. Min Act: -0.1700

Data Index: 5616466 (Open Web Text)

Max Activating Token Index: 983

Text #1

Max Range: 3.3707. Min Range: -3.3707

Max Act: 3.3511. Min Act: -0.1700

Data Index: 6128503 (Open Web Text)

Max Activating Token Index: 252

Text #2

Max Range: 3.3707. Min Range: -3.3707

Max Act: 3.2884. Min Act: -0.1700

Data Index: 3949401 (Open Web Text)

Max Activating Token Index: 880

Text #3

Max Range: 3.3707. Min Range: -3.3707

Max Act: 3.3013. Min Act: -0.1700

Data Index: 210614 (Open Web Text)

Max Activating Token Index: 285

Text #4

Max Range: 3.3707. Min Range: -3.3707

Max Act: 3.2985. Min Act: -0.1700

Data Index: 2798374 (Open Web Text)

Max Activating Token Index: 452

Text #5

Max Range: 3.3707. Min Range: -3.3707

Max Act: 3.2659. Min Act: -0.1700

Data Index: 4689707 (Open Web Text)

Max Activating Token Index: 856

Text #6

Max Range: 3.3707. Min Range: -3.3707

Max Act: 3.2545. Min Act: -0.1700

Data Index: 2448981 (Open Web Text)

Max Activating Token Index: 966

Text #7

Max Range: 3.3707. Min Range: -3.3707

Max Act: 3.2112. Min Act: -0.1700

Data Index: 8696402 (Open Web Text)

Max Activating Token Index: 177

Text #8

Max Range: 3.3707. Min Range: -3.3707

Max Act: 3.1860. Min Act: -0.1700

Data Index: 3686751 (Open Web Text)

Max Activating Token Index: 935

Text #9

Max Range: 3.3707. Min Range: -3.3707

Max Act: 3.1730. Min Act: -0.1700

Data Index: 3340468 (Open Web Text)

Max Activating Token Index: 917

Text #10

Max Range: 3.3707. Min Range: -3.3707

Max Act: 3.1668. Min Act: -0.1700

Data Index: 7725423 (Open Web Text)

Max Activating Token Index: 921

Text #11

Max Range: 3.3707. Min Range: -3.3707

Max Act: 3.1623. Min Act: -0.1700

Data Index: 6885111 (Open Web Text)

Max Activating Token Index: 584

Text #12

Max Range: 3.3707. Min Range: -3.3707

Max Act: 3.1519. Min Act: -0.1700

Data Index: 5945319 (Open Web Text)

Max Activating Token Index: 709

Text #13

Max Range: 3.3707. Min Range: -3.3707

Max Act: 3.1739. Min Act: -0.1700

Data Index: 3997529 (Open Web Text)

Max Activating Token Index: 883

Text #14

Max Range: 3.3707. Min Range: -3.3707

Max Act: 3.1693. Min Act: -0.1700

Data Index: 391692 (Open Web Text)

Max Activating Token Index: 591

Text #15

Max Range: 3.3707. Min Range: -3.3707

Max Act: 3.1610. Min Act: -0.1700

Data Index: 3908285 (Open Web Text)

Max Activating Token Index: 915

Text #16

Max Range: 3.3707. Min Range: -3.3707

Max Act: 3.1879. Min Act: -0.1700

Data Index: 4602401 (Open Web Text)

Max Activating Token Index: 836

Text #17

Max Range: 3.3707. Min Range: -3.3707

Max Act: 3.1791. Min Act: -0.1700

Data Index: 288387 (Open Web Text)

Max Activating Token Index: 694

Text #18

Max Range: 3.3707. Min Range: -3.3707

Max Act: 3.1428. Min Act: -0.1700

Data Index: 3293736 (Open Web Text)

Max Activating Token Index: 501

Text #19

Max Range: 3.3707. Min Range: -3.3707

Max Act: 3.1651. Min Act: -0.1700

Data Index: 4906613 (Open Web Text)

Max Activating Token Index: 874