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

Dataset: Open Web Text

Neuron 281 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: 4.6810. Min Range: -4.6810

Max Act: 4.6810. Min Act: -0.1700

Data Index: 2801436 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 4.6810. Min Range: -4.6810

Max Act: 4.6016. Min Act: -0.1700

Data Index: 4764100 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 4.6810. Min Range: -4.6810

Max Act: 4.5800. Min Act: -0.1700

Data Index: 1848764 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 4.6810. Min Range: -4.6810

Max Act: 4.5741. Min Act: -0.1700

Data Index: 1335626 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.6810. Min Range: -4.6810

Max Act: 4.5710. Min Act: -0.1700

Data Index: 6586928 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.6810. Min Range: -4.6810

Max Act: 4.5447. Min Act: -0.1700

Data Index: 2712514 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 4.6810. Min Range: -4.6810

Max Act: 4.5569. Min Act: -0.1700

Data Index: 2824297 (Open Web Text)

Max Activating Token Index: 11

Text #7

Max Range: 4.6810. Min Range: -4.6810

Max Act: 4.4728. Min Act: -0.1700

Data Index: 880667 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 4.6810. Min Range: -4.6810

Max Act: 4.4685. Min Act: -0.1700

Data Index: 7684502 (Open Web Text)

Max Activating Token Index: 16

Text #9

Max Range: 4.6810. Min Range: -4.6810

Max Act: 4.4974. Min Act: -0.1700

Data Index: 4191597 (Open Web Text)

Max Activating Token Index: 10

Text #10

Max Range: 4.6810. Min Range: -4.6810

Max Act: 4.4772. Min Act: -0.1700

Data Index: 2345035 (Open Web Text)

Max Activating Token Index: 12

Text #11

Max Range: 4.6810. Min Range: -4.6810

Max Act: 4.4491. Min Act: -0.1700

Data Index: 2799956 (Open Web Text)

Max Activating Token Index: 15

Text #12

Max Range: 4.6810. Min Range: -4.6810

Max Act: 4.4576. Min Act: -0.1700

Data Index: 6098887 (Open Web Text)

Max Activating Token Index: 24

Text #13

Max Range: 4.6810. Min Range: -4.6810

Max Act: 4.4557. Min Act: -0.1700

Data Index: 1687619 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 4.6810. Min Range: -4.6810

Max Act: 4.4650. Min Act: -0.1700

Data Index: 4265525 (Open Web Text)

Max Activating Token Index: 20

Text #15

Max Range: 4.6810. Min Range: -4.6810

Max Act: 4.4403. Min Act: -0.1700

Data Index: 2206699 (Open Web Text)

Max Activating Token Index: 52

Text #16

Max Range: 4.6810. Min Range: -4.6810

Max Act: 4.4419. Min Act: -0.1700

Data Index: 593463 (Open Web Text)

Max Activating Token Index: 37

Text #17

Max Range: 4.6810. Min Range: -4.6810

Max Act: 4.4567. Min Act: -0.1700

Data Index: 5948336 (Open Web Text)

Max Activating Token Index: 14

Text #18

Max Range: 4.6810. Min Range: -4.6810

Max Act: 4.4697. Min Act: -0.1700

Data Index: 5918229 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 4.6810. Min Range: -4.6810

Max Act: 4.4628. Min Act: -0.1700

Data Index: 173306 (Open Web Text)

Max Activating Token Index: 7