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

Dataset: Open Web Text

Neuron 1186 in Layer 1

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: 1.7595. Min Range: -1.7595

Max Act: 1.7595. Min Act: -0.1700

Data Index: 6988560 (Open Web Text)

Max Activating Token Index: 109

Text #1

Max Range: 1.7595. Min Range: -1.7595

Max Act: 1.7265. Min Act: -0.1700

Data Index: 7471766 (Open Web Text)

Max Activating Token Index: 548

Text #2

Max Range: 1.7595. Min Range: -1.7595

Max Act: 1.6900. Min Act: -0.1694

Data Index: 2733050 (Open Web Text)

Max Activating Token Index: 76

Text #3

Max Range: 1.7595. Min Range: -1.7595

Max Act: 1.6842. Min Act: -0.1700

Data Index: 3501046 (Open Web Text)

Max Activating Token Index: 150

Text #4

Max Range: 1.7595. Min Range: -1.7595

Max Act: 1.6840. Min Act: -0.1700

Data Index: 6743884 (Open Web Text)

Max Activating Token Index: 726

Text #5

Max Range: 1.7595. Min Range: -1.7595

Max Act: 1.6787. Min Act: -0.1685

Data Index: 6116694 (Open Web Text)

Max Activating Token Index: 578

Text #6

Max Range: 1.7595. Min Range: -1.7595

Max Act: 1.6793. Min Act: -0.1700

Data Index: 1321509 (Open Web Text)

Max Activating Token Index: 635

Text #7

Max Range: 1.7595. Min Range: -1.7595

Max Act: 1.6698. Min Act: -0.1700

Data Index: 3140694 (Open Web Text)

Max Activating Token Index: 234

Text #8

Max Range: 1.7595. Min Range: -1.7595

Max Act: 1.6694. Min Act: -0.1700

Data Index: 3953209 (Open Web Text)

Max Activating Token Index: 442

Text #9

Max Range: 1.7595. Min Range: -1.7595

Max Act: 1.6556. Min Act: -0.1683

Data Index: 3884640 (Open Web Text)

Max Activating Token Index: 416

Text #10

Max Range: 1.7595. Min Range: -1.7595

Max Act: 1.6628. Min Act: -0.1700

Data Index: 4415608 (Open Web Text)

Max Activating Token Index: 559

Text #11

Max Range: 1.7595. Min Range: -1.7595

Max Act: 1.6442. Min Act: -0.1682

Data Index: 4700460 (Open Web Text)

Max Activating Token Index: 198

Text #12

Max Range: 1.7595. Min Range: -1.7595

Max Act: 1.6302. Min Act: -0.1696

Data Index: 7010435 (Open Web Text)

Max Activating Token Index: 990

Text #13

Max Range: 1.7595. Min Range: -1.7595

Max Act: 1.6409. Min Act: -0.1700

Data Index: 2501944 (Open Web Text)

Max Activating Token Index: 436

Text #14

Max Range: 1.7595. Min Range: -1.7595

Max Act: 1.6474. Min Act: -0.1700

Data Index: 2487203 (Open Web Text)

Max Activating Token Index: 684

Text #15

Max Range: 1.7595. Min Range: -1.7595

Max Act: 1.6386. Min Act: -0.1680

Data Index: 7387218 (Open Web Text)

Max Activating Token Index: 118

Text #16

Max Range: 1.7595. Min Range: -1.7595

Max Act: 1.6291. Min Act: -0.1700

Data Index: 1898036 (Open Web Text)

Max Activating Token Index: 784

Text #17

Max Range: 1.7595. Min Range: -1.7595

Max Act: 1.6337. Min Act: -0.1700

Data Index: 1818388 (Open Web Text)

Max Activating Token Index: 474

Text #18

Max Range: 1.7595. Min Range: -1.7595

Max Act: 1.6291. Min Act: -0.1700

Data Index: 2812712 (Open Web Text)

Max Activating Token Index: 520

Text #19

Max Range: 1.7595. Min Range: -1.7595

Max Act: 1.6362. Min Act: -0.1698

Data Index: 1016865 (Open Web Text)

Max Activating Token Index: 82