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

Dataset: Open Web Text

Neuron 1214 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: 3.4659. Min Range: -3.4659

Max Act: 3.4659. Min Act: -0.1700

Data Index: 4247318 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 3.4659. Min Range: -3.4659

Max Act: 3.4029. Min Act: -0.1700

Data Index: 2898107 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.4659. Min Range: -3.4659

Max Act: 3.4032. Min Act: -0.1700

Data Index: 4338065 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.4659. Min Range: -3.4659

Max Act: 3.3972. Min Act: -0.1700

Data Index: 3219456 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.4659. Min Range: -3.4659

Max Act: 3.3799. Min Act: -0.1700

Data Index: 903681 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.4659. Min Range: -3.4659

Max Act: 3.3864. Min Act: -0.1700

Data Index: 727666 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.4659. Min Range: -3.4659

Max Act: 3.3833. Min Act: -0.1700

Data Index: 1638645 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.4659. Min Range: -3.4659

Max Act: 3.3857. Min Act: -0.1700

Data Index: 2849717 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.4659. Min Range: -3.4659

Max Act: 3.3717. Min Act: -0.1700

Data Index: 8652619 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.4659. Min Range: -3.4659

Max Act: 3.3723. Min Act: -0.1700

Data Index: 2029220 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.4659. Min Range: -3.4659

Max Act: 3.3646. Min Act: -0.1700

Data Index: 5279751 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.4659. Min Range: -3.4659

Max Act: 3.3641. Min Act: -0.1700

Data Index: 2016452 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.4659. Min Range: -3.4659

Max Act: 3.3429. Min Act: -0.1700

Data Index: 7184976 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 3.4659. Min Range: -3.4659

Max Act: 3.3465. Min Act: -0.1700

Data Index: 4592 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.4659. Min Range: -3.4659

Max Act: 3.3403. Min Act: -0.1700

Data Index: 1691149 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.4659. Min Range: -3.4659

Max Act: 3.3311. Min Act: -0.1700

Data Index: 6477210 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.4659. Min Range: -3.4659

Max Act: 3.3199. Min Act: -0.1700

Data Index: 4651538 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.4659. Min Range: -3.4659

Max Act: 3.3284. Min Act: -0.1700

Data Index: 3121239 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.4659. Min Range: -3.4659

Max Act: 3.3226. Min Act: -0.1700

Data Index: 5096888 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.4659. Min Range: -3.4659

Max Act: 3.3311. Min Act: -0.1700

Data Index: 8342343 (Open Web Text)

Max Activating Token Index: 3