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

Dataset: Open Web Text

Neuron 1792 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: 4.4851. Min Range: -4.4851

Max Act: 4.4851. Min Act: -0.1700

Data Index: 5547899 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.4851. Min Range: -4.4851

Max Act: 4.4697. Min Act: -0.1700

Data Index: 1687696 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 4.4851. Min Range: -4.4851

Max Act: 4.4028. Min Act: -0.1700

Data Index: 6491809 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.4851. Min Range: -4.4851

Max Act: 4.4057. Min Act: -0.1700

Data Index: 8607208 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 4.4851. Min Range: -4.4851

Max Act: 4.4085. Min Act: -0.1700

Data Index: 5687702 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 4.4851. Min Range: -4.4851

Max Act: 4.4001. Min Act: -0.1700

Data Index: 93048 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 4.4851. Min Range: -4.4851

Max Act: 4.4068. Min Act: -0.1700

Data Index: 1564439 (Open Web Text)

Max Activating Token Index: 27

Text #7

Max Range: 4.4851. Min Range: -4.4851

Max Act: 4.4169. Min Act: -0.1700

Data Index: 1452420 (Open Web Text)

Max Activating Token Index: 18

Text #8

Max Range: 4.4851. Min Range: -4.4851

Max Act: 4.3859. Min Act: -0.1700

Data Index: 992947 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 4.4851. Min Range: -4.4851

Max Act: 4.3900. Min Act: -0.1700

Data Index: 5637249 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 4.4851. Min Range: -4.4851

Max Act: 4.3783. Min Act: -0.1700

Data Index: 5595383 (Open Web Text)

Max Activating Token Index: 11

Text #11

Max Range: 4.4851. Min Range: -4.4851

Max Act: 4.3834. Min Act: -0.1700

Data Index: 6166058 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 4.4851. Min Range: -4.4851

Max Act: 4.3795. Min Act: -0.1700

Data Index: 2154779 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 4.4851. Min Range: -4.4851

Max Act: 4.3882. Min Act: -0.1700

Data Index: 2292948 (Open Web Text)

Max Activating Token Index: 11

Text #14

Max Range: 4.4851. Min Range: -4.4851

Max Act: 4.3735. Min Act: -0.1700

Data Index: 1826863 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 4.4851. Min Range: -4.4851

Max Act: 4.3386. Min Act: -0.1700

Data Index: 3937055 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 4.4851. Min Range: -4.4851

Max Act: 4.3415. Min Act: -0.1700

Data Index: 4045688 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 4.4851. Min Range: -4.4851

Max Act: 4.3644. Min Act: -0.1700

Data Index: 4225150 (Open Web Text)

Max Activating Token Index: 51

Text #18

Max Range: 4.4851. Min Range: -4.4851

Max Act: 4.3491. Min Act: -0.1700

Data Index: 4467271 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 4.4851. Min Range: -4.4851

Max Act: 4.3564. Min Act: -0.1700

Data Index: 1948111 (Open Web Text)

Max Activating Token Index: 7