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

Dataset: Open Web Text

Neuron 1396 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: 2.4796. Min Range: -2.4796

Max Act: 2.4796. Min Act: -0.1700

Data Index: 3840957 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 2.4796. Min Range: -2.4796

Max Act: 2.4272. Min Act: -0.1700

Data Index: 1406773 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 2.4796. Min Range: -2.4796

Max Act: 2.4276. Min Act: -0.1700

Data Index: 5676873 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 2.4796. Min Range: -2.4796

Max Act: 2.4008. Min Act: -0.1700

Data Index: 3565593 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 2.4796. Min Range: -2.4796

Max Act: 2.3961. Min Act: -0.1700

Data Index: 1282959 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 2.4796. Min Range: -2.4796

Max Act: 2.3797. Min Act: -0.1700

Data Index: 1599687 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 2.4796. Min Range: -2.4796

Max Act: 2.3798. Min Act: -0.1700

Data Index: 6650985 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 2.4796. Min Range: -2.4796

Max Act: 2.3917. Min Act: -0.1700

Data Index: 5444092 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 2.4796. Min Range: -2.4796

Max Act: 2.3862. Min Act: -0.1700

Data Index: 5314368 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 2.4796. Min Range: -2.4796

Max Act: 2.3899. Min Act: -0.1700

Data Index: 7797577 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 2.4796. Min Range: -2.4796

Max Act: 2.3825. Min Act: -0.1700

Data Index: 5489982 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 2.4796. Min Range: -2.4796

Max Act: 2.3697. Min Act: -0.1700

Data Index: 2408897 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 2.4796. Min Range: -2.4796

Max Act: 2.3781. Min Act: -0.1700

Data Index: 2032863 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 2.4796. Min Range: -2.4796

Max Act: 2.3681. Min Act: -0.1700

Data Index: 7625042 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 2.4796. Min Range: -2.4796

Max Act: 2.3825. Min Act: -0.1700

Data Index: 3698097 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 2.4796. Min Range: -2.4796

Max Act: 2.3678. Min Act: -0.1700

Data Index: 7592328 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 2.4796. Min Range: -2.4796

Max Act: 2.3664. Min Act: -0.1700

Data Index: 5694776 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 2.4796. Min Range: -2.4796

Max Act: 2.3489. Min Act: -0.1700

Data Index: 4977009 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 2.4796. Min Range: -2.4796

Max Act: 2.3523. Min Act: -0.1700

Data Index: 85082 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 2.4796. Min Range: -2.4796

Max Act: 2.3568. Min Act: -0.1700

Data Index: 2851749 (Open Web Text)

Max Activating Token Index: 7