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

Dataset: Open Web Text

Neuron 103 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: 5.8624. Min Range: -5.8624

Max Act: 5.8522. Min Act: -0.1700

Data Index: 8045063 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 5.8624. Min Range: -5.8624

Max Act: 5.8624. Min Act: -0.1700

Data Index: 6572585 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 5.8624. Min Range: -5.8624

Max Act: 5.8359. Min Act: -0.1700

Data Index: 3669238 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 5.8624. Min Range: -5.8624

Max Act: 5.7715. Min Act: -0.1700

Data Index: 3344226 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 5.8624. Min Range: -5.8624

Max Act: 5.7555. Min Act: -0.1700

Data Index: 5544302 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 5.8624. Min Range: -5.8624

Max Act: 5.7515. Min Act: -0.1700

Data Index: 1824390 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 5.8624. Min Range: -5.8624

Max Act: 5.7393. Min Act: -0.1700

Data Index: 5265718 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 5.8624. Min Range: -5.8624

Max Act: 5.7069. Min Act: -0.1700

Data Index: 7520842 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 5.8624. Min Range: -5.8624

Max Act: 5.7084. Min Act: -0.1700

Data Index: 4893352 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 5.8624. Min Range: -5.8624

Max Act: 5.6857. Min Act: -0.1700

Data Index: 7925848 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 5.8624. Min Range: -5.8624

Max Act: 5.6849. Min Act: -0.1700

Data Index: 8486786 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 5.8624. Min Range: -5.8624

Max Act: 5.6856. Min Act: -0.1700

Data Index: 3434500 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 5.8624. Min Range: -5.8624

Max Act: 5.6985. Min Act: -0.1700

Data Index: 875877 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 5.8624. Min Range: -5.8624

Max Act: 5.6783. Min Act: -0.1700

Data Index: 4369117 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 5.8624. Min Range: -5.8624

Max Act: 5.6419. Min Act: -0.1700

Data Index: 6784308 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 5.8624. Min Range: -5.8624

Max Act: 5.6451. Min Act: -0.1700

Data Index: 7125103 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 5.8624. Min Range: -5.8624

Max Act: 5.6693. Min Act: -0.1700

Data Index: 4131856 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 5.8624. Min Range: -5.8624

Max Act: 5.6480. Min Act: -0.1700

Data Index: 5168140 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 5.8624. Min Range: -5.8624

Max Act: 5.6649. Min Act: -0.1700

Data Index: 5908859 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 5.8624. Min Range: -5.8624

Max Act: 5.6605. Min Act: -0.1700

Data Index: 2976896 (Open Web Text)

Max Activating Token Index: 3