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

Dataset: Open Web Text

Neuron 1288 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: 3.5555. Min Range: -3.5555

Max Act: 3.5555. Min Act: -0.1700

Data Index: 6706850 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.5469. Min Act: -0.1700

Data Index: 5763922 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.5116. Min Act: -0.1700

Data Index: 5550586 (Open Web Text)

Max Activating Token Index: 610

Text #3

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.4938. Min Act: -0.1700

Data Index: 1437162 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.4887. Min Act: -0.1700

Data Index: 8629546 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.4824. Min Act: -0.1700

Data Index: 7201580 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.4604. Min Act: -0.1700

Data Index: 8062776 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.4590. Min Act: -0.1700

Data Index: 8227981 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.4492. Min Act: -0.1700

Data Index: 4456352 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.4268. Min Act: -0.1700

Data Index: 5340412 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.4324. Min Act: -0.1700

Data Index: 6314784 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.4178. Min Act: -0.1700

Data Index: 3162553 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.4285. Min Act: -0.1700

Data Index: 4910750 (Open Web Text)

Max Activating Token Index: 8

Text #13

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.4189. Min Act: -0.1700

Data Index: 503382 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.3974. Min Act: -0.1700

Data Index: 158775 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.4119. Min Act: -0.1700

Data Index: 6623379 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.4062. Min Act: -0.1700

Data Index: 8247383 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.3792. Min Act: -0.1700

Data Index: 1138677 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.3931. Min Act: -0.1700

Data Index: 7491608 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.3788. Min Act: -0.1700

Data Index: 4909874 (Open Web Text)

Max Activating Token Index: 3