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

Dataset: Open Web Text

Neuron 1204 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: 4.6378. Min Range: -4.6378

Max Act: 4.6378. Min Act: -0.1700

Data Index: 6769323 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.6378. Min Range: -4.6378

Max Act: 4.5395. Min Act: -0.1700

Data Index: 3475993 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 4.6378. Min Range: -4.6378

Max Act: 4.5010. Min Act: -0.1700

Data Index: 2470499 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 4.6378. Min Range: -4.6378

Max Act: 4.5010. Min Act: -0.1700

Data Index: 5344900 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 4.6378. Min Range: -4.6378

Max Act: 4.4755. Min Act: -0.1700

Data Index: 4499978 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 4.6378. Min Range: -4.6378

Max Act: 4.4855. Min Act: -0.1700

Data Index: 1801445 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 4.6378. Min Range: -4.6378

Max Act: 4.4837. Min Act: -0.1700

Data Index: 7097608 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 4.6378. Min Range: -4.6378

Max Act: 4.4749. Min Act: -0.1700

Data Index: 2987325 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 4.6378. Min Range: -4.6378

Max Act: 4.4765. Min Act: -0.1700

Data Index: 6121820 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 4.6378. Min Range: -4.6378

Max Act: 4.4865. Min Act: -0.1700

Data Index: 5206613 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 4.6378. Min Range: -4.6378

Max Act: 4.4668. Min Act: -0.1700

Data Index: 7326089 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 4.6378. Min Range: -4.6378

Max Act: 4.4847. Min Act: -0.1700

Data Index: 7204574 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 4.6378. Min Range: -4.6378

Max Act: 4.4593. Min Act: -0.1700

Data Index: 7508652 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 4.6378. Min Range: -4.6378

Max Act: 4.4594. Min Act: -0.1700

Data Index: 1674011 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 4.6378. Min Range: -4.6378

Max Act: 4.4252. Min Act: -0.1700

Data Index: 6894823 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 4.6378. Min Range: -4.6378

Max Act: 4.4434. Min Act: -0.1700

Data Index: 1752389 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 4.6378. Min Range: -4.6378

Max Act: 4.4365. Min Act: -0.1700

Data Index: 3562172 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 4.6378. Min Range: -4.6378

Max Act: 4.3949. Min Act: -0.1700

Data Index: 493757 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 4.6378. Min Range: -4.6378

Max Act: 4.3882. Min Act: -0.1700

Data Index: 2396252 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 4.6378. Min Range: -4.6378

Max Act: 4.3882. Min Act: -0.1700

Data Index: 1204539 (Open Web Text)

Max Activating Token Index: 3