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

Dataset: Open Web Text

Neuron 1992 in Layer 5

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: 5.8029. Min Range: -5.8029

Max Act: 5.8029. Min Act: -0.1700

Data Index: 5826872 (Open Web Text)

Max Activating Token Index: 810

Text #1

Max Range: 5.8029. Min Range: -5.8029

Max Act: 5.5787. Min Act: -0.1700

Data Index: 3718937 (Open Web Text)

Max Activating Token Index: 1015

Text #2

Max Range: 5.8029. Min Range: -5.8029

Max Act: 5.3584. Min Act: -0.1700

Data Index: 8021659 (Open Web Text)

Max Activating Token Index: 808

Text #3

Max Range: 5.8029. Min Range: -5.8029

Max Act: 5.1553. Min Act: -0.1700

Data Index: 6415586 (Open Web Text)

Max Activating Token Index: 148

Text #4

Max Range: 5.8029. Min Range: -5.8029

Max Act: 5.1875. Min Act: -0.1700

Data Index: 1630620 (Open Web Text)

Max Activating Token Index: 376

Text #5

Max Range: 5.8029. Min Range: -5.8029

Max Act: 5.1882. Min Act: -0.1700

Data Index: 373662 (Open Web Text)

Max Activating Token Index: 337

Text #6

Max Range: 5.8029. Min Range: -5.8029

Max Act: 5.1745. Min Act: -0.1700

Data Index: 3379218 (Open Web Text)

Max Activating Token Index: 322

Text #7

Max Range: 5.8029. Min Range: -5.8029

Max Act: 5.1307. Min Act: -0.1700

Data Index: 7469303 (Open Web Text)

Max Activating Token Index: 910

Text #8

Max Range: 5.8029. Min Range: -5.8029

Max Act: 5.1789. Min Act: -0.1700

Data Index: 5939589 (Open Web Text)

Max Activating Token Index: 817

Text #9

Max Range: 5.8029. Min Range: -5.8029

Max Act: 5.1271. Min Act: -0.1700

Data Index: 2638418 (Open Web Text)

Max Activating Token Index: 841

Text #10

Max Range: 5.8029. Min Range: -5.8029

Max Act: 5.0790. Min Act: -0.1700

Data Index: 2593349 (Open Web Text)

Max Activating Token Index: 743

Text #11

Max Range: 5.8029. Min Range: -5.8029

Max Act: 5.0996. Min Act: -0.1700

Data Index: 1843170 (Open Web Text)

Max Activating Token Index: 492

Text #12

Max Range: 5.8029. Min Range: -5.8029

Max Act: 5.0776. Min Act: -0.1700

Data Index: 5541147 (Open Web Text)

Max Activating Token Index: 361

Text #13

Max Range: 5.8029. Min Range: -5.8029

Max Act: 5.0733. Min Act: -0.1699

Data Index: 7230420 (Open Web Text)

Max Activating Token Index: 667

Text #14

Max Range: 5.8029. Min Range: -5.8029

Max Act: 5.0408. Min Act: -0.1700

Data Index: 1449130 (Open Web Text)

Max Activating Token Index: 540

Text #15

Max Range: 5.8029. Min Range: -5.8029

Max Act: 5.0526. Min Act: -0.1700

Data Index: 1878626 (Open Web Text)

Max Activating Token Index: 773

Text #16

Max Range: 5.8029. Min Range: -5.8029

Max Act: 5.0309. Min Act: -0.1700

Data Index: 1698005 (Open Web Text)

Max Activating Token Index: 684

Text #17

Max Range: 5.8029. Min Range: -5.8029

Max Act: 5.0380. Min Act: -0.1700

Data Index: 1737640 (Open Web Text)

Max Activating Token Index: 885

Text #18

Max Range: 5.8029. Min Range: -5.8029

Max Act: 5.0225. Min Act: -0.1700

Data Index: 6576368 (Open Web Text)

Max Activating Token Index: 742

Text #19

Max Range: 5.8029. Min Range: -5.8029

Max Act: 4.9734. Min Act: -0.1700

Data Index: 7173456 (Open Web Text)

Max Activating Token Index: 610