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

Dataset: Open Web Text

Neuron 1369 in Layer 3

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: 2.2552. Min Range: -2.2552

Max Act: 2.2552. Min Act: -0.1700

Data Index: 4730847 (Open Web Text)

Max Activating Token Index: 980

Text #1

Max Range: 2.2552. Min Range: -2.2552

Max Act: 2.2137. Min Act: -0.1700

Data Index: 1756507 (Open Web Text)

Max Activating Token Index: 414

Text #2

Max Range: 2.2552. Min Range: -2.2552

Max Act: 2.1893. Min Act: -0.1700

Data Index: 8151470 (Open Web Text)

Max Activating Token Index: 557

Text #3

Max Range: 2.2552. Min Range: -2.2552

Max Act: 2.2022. Min Act: -0.1700

Data Index: 5702480 (Open Web Text)

Max Activating Token Index: 156

Text #4

Max Range: 2.2552. Min Range: -2.2552

Max Act: 2.2016. Min Act: -0.1700

Data Index: 1549046 (Open Web Text)

Max Activating Token Index: 1006

Text #5

Max Range: 2.2552. Min Range: -2.2552

Max Act: 2.1743. Min Act: -0.1700

Data Index: 7309056 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 2.2552. Min Range: -2.2552

Max Act: 2.1938. Min Act: -0.1700

Data Index: 3488081 (Open Web Text)

Max Activating Token Index: 878

Text #7

Max Range: 2.2552. Min Range: -2.2552

Max Act: 2.1983. Min Act: -0.1700

Data Index: 3236428 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 2.2552. Min Range: -2.2552

Max Act: 2.1643. Min Act: -0.1700

Data Index: 5928947 (Open Web Text)

Max Activating Token Index: 453

Text #9

Max Range: 2.2552. Min Range: -2.2552

Max Act: 2.1673. Min Act: -0.1700

Data Index: 1535493 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 2.2552. Min Range: -2.2552

Max Act: 2.1661. Min Act: -0.1700

Data Index: 5026778 (Open Web Text)

Max Activating Token Index: 562

Text #11

Max Range: 2.2552. Min Range: -2.2552

Max Act: 2.1655. Min Act: -0.1700

Data Index: 5666342 (Open Web Text)

Max Activating Token Index: 524

Text #12

Max Range: 2.2552. Min Range: -2.2552

Max Act: 2.1569. Min Act: -0.1700

Data Index: 6620077 (Open Web Text)

Max Activating Token Index: 944

Text #13

Max Range: 2.2552. Min Range: -2.2552

Max Act: 2.1672. Min Act: -0.1700

Data Index: 1458964 (Open Web Text)

Max Activating Token Index: 379

Text #14

Max Range: 2.2552. Min Range: -2.2552

Max Act: 2.1579. Min Act: -0.1700

Data Index: 5281715 (Open Web Text)

Max Activating Token Index: 504

Text #15

Max Range: 2.2552. Min Range: -2.2552

Max Act: 2.1659. Min Act: -0.1700

Data Index: 8579870 (Open Web Text)

Max Activating Token Index: 828

Text #16

Max Range: 2.2552. Min Range: -2.2552

Max Act: 2.1684. Min Act: -0.1700

Data Index: 3171787 (Open Web Text)

Max Activating Token Index: 12

Text #17

Max Range: 2.2552. Min Range: -2.2552

Max Act: 2.1385. Min Act: -0.1700

Data Index: 3431745 (Open Web Text)

Max Activating Token Index: 477

Text #18

Max Range: 2.2552. Min Range: -2.2552

Max Act: 2.1563. Min Act: -0.1700

Data Index: 72550 (Open Web Text)

Max Activating Token Index: 206

Text #19

Max Range: 2.2552. Min Range: -2.2552

Max Act: 2.1480. Min Act: -0.1700

Data Index: 3491469 (Open Web Text)

Max Activating Token Index: 345