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

Dataset: Open Web Text

Neuron 1777 in Layer 0

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: 2.6652. Min Range: -2.6652

Max Act: 2.6652. Min Act: -0.1700

Data Index: 1877549 (Open Web Text)

Max Activating Token Index: 1010

Text #1

Max Range: 2.6652. Min Range: -2.6652

Max Act: 2.6026. Min Act: -0.1700

Data Index: 2883508 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 2.6652. Min Range: -2.6652

Max Act: 2.5761. Min Act: -0.1700

Data Index: 4889816 (Open Web Text)

Max Activating Token Index: 751

Text #3

Max Range: 2.6652. Min Range: -2.6652

Max Act: 2.5978. Min Act: -0.1700

Data Index: 8249038 (Open Web Text)

Max Activating Token Index: 301

Text #4

Max Range: 2.6652. Min Range: -2.6652

Max Act: 2.5799. Min Act: -0.1700

Data Index: 4174320 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 2.6652. Min Range: -2.6652

Max Act: 2.5853. Min Act: -0.1700

Data Index: 8473189 (Open Web Text)

Max Activating Token Index: 829

Text #6

Max Range: 2.6652. Min Range: -2.6652

Max Act: 2.5692. Min Act: -0.1700

Data Index: 7404490 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 2.6652. Min Range: -2.6652

Max Act: 2.5593. Min Act: -0.1700

Data Index: 8587293 (Open Web Text)

Max Activating Token Index: 872

Text #8

Max Range: 2.6652. Min Range: -2.6652

Max Act: 2.5748. Min Act: -0.1700

Data Index: 1881021 (Open Web Text)

Max Activating Token Index: 40

Text #9

Max Range: 2.6652. Min Range: -2.6652

Max Act: 2.5789. Min Act: -0.1700

Data Index: 2486323 (Open Web Text)

Max Activating Token Index: 512

Text #10

Max Range: 2.6652. Min Range: -2.6652

Max Act: 2.5640. Min Act: -0.1700

Data Index: 5409629 (Open Web Text)

Max Activating Token Index: 452

Text #11

Max Range: 2.6652. Min Range: -2.6652

Max Act: 2.5482. Min Act: -0.1700

Data Index: 7404487 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 2.6652. Min Range: -2.6652

Max Act: 2.5681. Min Act: -0.1700

Data Index: 1872183 (Open Web Text)

Max Activating Token Index: 667

Text #13

Max Range: 2.6652. Min Range: -2.6652

Max Act: 2.5648. Min Act: -0.1700

Data Index: 7453532 (Open Web Text)

Max Activating Token Index: 681

Text #14

Max Range: 2.6652. Min Range: -2.6652

Max Act: 2.5656. Min Act: -0.1700

Data Index: 264032 (Open Web Text)

Max Activating Token Index: 664

Text #15

Max Range: 2.6652. Min Range: -2.6652

Max Act: 2.5511. Min Act: -0.1700

Data Index: 1466739 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 2.6652. Min Range: -2.6652

Max Act: 2.5608. Min Act: -0.1700

Data Index: 619774 (Open Web Text)

Max Activating Token Index: 600

Text #17

Max Range: 2.6652. Min Range: -2.6652

Max Act: 2.5632. Min Act: -0.1700

Data Index: 4513648 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 2.6652. Min Range: -2.6652

Max Act: 2.5475. Min Act: -0.1700

Data Index: 7977856 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 2.6652. Min Range: -2.6652

Max Act: 2.5511. Min Act: -0.1700

Data Index: 2240782 (Open Web Text)

Max Activating Token Index: 2