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

Dataset: Open Web Text

Neuron 576 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: 2.3447. Min Range: -2.3447

Max Act: 2.3447. Min Act: -0.1700

Data Index: 8807382 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 2.3447. Min Range: -2.3447

Max Act: 2.3355. Min Act: -0.1700

Data Index: 473207 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 2.3447. Min Range: -2.3447

Max Act: 2.3355. Min Act: -0.1700

Data Index: 4563527 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 2.3447. Min Range: -2.3447

Max Act: 2.3434. Min Act: -0.1700

Data Index: 7316655 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 2.3447. Min Range: -2.3447

Max Act: 2.3258. Min Act: -0.1700

Data Index: 418349 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 2.3447. Min Range: -2.3447

Max Act: 2.3447. Min Act: -0.1700

Data Index: 3750251 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 2.3447. Min Range: -2.3447

Max Act: 2.3447. Min Act: -0.1700

Data Index: 7444374 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 2.3447. Min Range: -2.3447

Max Act: 2.3088. Min Act: -0.1700

Data Index: 5236226 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 2.3447. Min Range: -2.3447

Max Act: 2.2997. Min Act: -0.1700

Data Index: 5207199 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 2.3447. Min Range: -2.3447

Max Act: 2.3084. Min Act: -0.1700

Data Index: 8325378 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 2.3447. Min Range: -2.3447

Max Act: 2.2874. Min Act: -0.1700

Data Index: 8828114 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 2.3447. Min Range: -2.3447

Max Act: 2.2800. Min Act: -0.1700

Data Index: 3946797 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 2.3447. Min Range: -2.3447

Max Act: 2.2627. Min Act: -0.1700

Data Index: 4927052 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 2.3447. Min Range: -2.3447

Max Act: 2.2627. Min Act: -0.1700

Data Index: 7048887 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 2.3447. Min Range: -2.3447

Max Act: 2.2741. Min Act: -0.1700

Data Index: 1200709 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 2.3447. Min Range: -2.3447

Max Act: 2.2648. Min Act: -0.1700

Data Index: 2821488 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 2.3447. Min Range: -2.3447

Max Act: 2.2648. Min Act: -0.1700

Data Index: 2258217 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 2.3447. Min Range: -2.3447

Max Act: 2.2486. Min Act: -0.1700

Data Index: 922584 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 2.3447. Min Range: -2.3447

Max Act: 2.2678. Min Act: -0.1700

Data Index: 1772052 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 2.3447. Min Range: -2.3447

Max Act: 2.2503. Min Act: -0.1700

Data Index: 2159689 (Open Web Text)

Max Activating Token Index: 2