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

Dataset: Open Web Text

Neuron 590 in Layer 2

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: 1.7330. Min Range: -1.7330

Max Act: 1.7330. Min Act: -0.1700

Data Index: 898820 (Open Web Text)

Max Activating Token Index: 153

Text #1

Max Range: 1.7330. Min Range: -1.7330

Max Act: 1.6756. Min Act: -0.1680

Data Index: 278745 (Open Web Text)

Max Activating Token Index: 299

Text #2

Max Range: 1.7330. Min Range: -1.7330

Max Act: 1.6673. Min Act: -0.1700

Data Index: 7665443 (Open Web Text)

Max Activating Token Index: 799

Text #3

Max Range: 1.7330. Min Range: -1.7330

Max Act: 1.6570. Min Act: -0.1700

Data Index: 3816308 (Open Web Text)

Max Activating Token Index: 333

Text #4

Max Range: 1.7330. Min Range: -1.7330

Max Act: 1.6590. Min Act: -0.1700

Data Index: 5343662 (Open Web Text)

Max Activating Token Index: 17

Text #5

Max Range: 1.7330. Min Range: -1.7330

Max Act: 1.6515. Min Act: -0.1700

Data Index: 8211137 (Open Web Text)

Max Activating Token Index: 420

Text #6

Max Range: 1.7330. Min Range: -1.7330

Max Act: 1.6357. Min Act: -0.1700

Data Index: 8388295 (Open Web Text)

Max Activating Token Index: 333

Text #7

Max Range: 1.7330. Min Range: -1.7330

Max Act: 1.6208. Min Act: -0.1700

Data Index: 3622372 (Open Web Text)

Max Activating Token Index: 836

Text #8

Max Range: 1.7330. Min Range: -1.7330

Max Act: 1.6309. Min Act: -0.1700

Data Index: 6476800 (Open Web Text)

Max Activating Token Index: 366

Text #9

Max Range: 1.7330. Min Range: -1.7330

Max Act: 1.6213. Min Act: -0.1700

Data Index: 2602416 (Open Web Text)

Max Activating Token Index: 498

Text #10

Max Range: 1.7330. Min Range: -1.7330

Max Act: 1.6039. Min Act: -0.1700

Data Index: 5305764 (Open Web Text)

Max Activating Token Index: 199

Text #11

Max Range: 1.7330. Min Range: -1.7330

Max Act: 1.6094. Min Act: -0.1697

Data Index: 8430443 (Open Web Text)

Max Activating Token Index: 500

Text #12

Max Range: 1.7330. Min Range: -1.7330

Max Act: 1.5811. Min Act: -0.1700

Data Index: 8594789 (Open Web Text)

Max Activating Token Index: 416

Text #13

Max Range: 1.7330. Min Range: -1.7330

Max Act: 1.5953. Min Act: -0.1700

Data Index: 5664652 (Open Web Text)

Max Activating Token Index: 334

Text #14

Max Range: 1.7330. Min Range: -1.7330

Max Act: 1.5862. Min Act: -0.1700

Data Index: 4073862 (Open Web Text)

Max Activating Token Index: 790

Text #15

Max Range: 1.7330. Min Range: -1.7330

Max Act: 1.6059. Min Act: -0.1700

Data Index: 2313832 (Open Web Text)

Max Activating Token Index: 1020

Text #16

Max Range: 1.7330. Min Range: -1.7330

Max Act: 1.5784. Min Act: -0.1700

Data Index: 4474666 (Open Web Text)

Max Activating Token Index: 113

Text #17

Max Range: 1.7330. Min Range: -1.7330

Max Act: 1.6013. Min Act: -0.1700

Data Index: 8671496 (Open Web Text)

Max Activating Token Index: 972

Text #18

Max Range: 1.7330. Min Range: -1.7330

Max Act: 1.5950. Min Act: -0.1700

Data Index: 5662124 (Open Web Text)

Max Activating Token Index: 692

Text #19

Max Range: 1.7330. Min Range: -1.7330

Max Act: 1.5759. Min Act: -0.1700

Data Index: 1239753 (Open Web Text)

Max Activating Token Index: 200