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

Dataset: Open Web Text

Neuron 539 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: 4.0642. Min Range: -4.0642

Max Act: 4.0504. Min Act: -0.1700

Data Index: 6188662 (Open Web Text)

Max Activating Token Index: 584

Text #1

Max Range: 4.0642. Min Range: -4.0642

Max Act: 4.0221. Min Act: -0.1700

Data Index: 7918228 (Open Web Text)

Max Activating Token Index: 487

Text #2

Max Range: 4.0642. Min Range: -4.0642

Max Act: 4.0102. Min Act: -0.1700

Data Index: 1230488 (Open Web Text)

Max Activating Token Index: 630

Text #3

Max Range: 4.0642. Min Range: -4.0642

Max Act: 4.0557. Min Act: -0.1700

Data Index: 8761786 (Open Web Text)

Max Activating Token Index: 692

Text #4

Max Range: 4.0642. Min Range: -4.0642

Max Act: 4.0103. Min Act: -0.1700

Data Index: 2585566 (Open Web Text)

Max Activating Token Index: 32

Text #5

Max Range: 4.0642. Min Range: -4.0642

Max Act: 4.0249. Min Act: -0.1700

Data Index: 6340017 (Open Web Text)

Max Activating Token Index: 540

Text #6

Max Range: 4.0642. Min Range: -4.0642

Max Act: 4.0287. Min Act: -0.1700

Data Index: 2931809 (Open Web Text)

Max Activating Token Index: 984

Text #7

Max Range: 4.0642. Min Range: -4.0642

Max Act: 4.0642. Min Act: -0.1700

Data Index: 1594308 (Open Web Text)

Max Activating Token Index: 260

Text #8

Max Range: 4.0642. Min Range: -4.0642

Max Act: 4.0226. Min Act: -0.1700

Data Index: 4158824 (Open Web Text)

Max Activating Token Index: 760

Text #9

Max Range: 4.0642. Min Range: -4.0642

Max Act: 3.9722. Min Act: -0.1700

Data Index: 1344001 (Open Web Text)

Max Activating Token Index: 382

Text #10

Max Range: 4.0642. Min Range: -4.0642

Max Act: 3.9799. Min Act: -0.1700

Data Index: 4831905 (Open Web Text)

Max Activating Token Index: 821

Text #11

Max Range: 4.0642. Min Range: -4.0642

Max Act: 3.9516. Min Act: -0.1700

Data Index: 8734787 (Open Web Text)

Max Activating Token Index: 601

Text #12

Max Range: 4.0642. Min Range: -4.0642

Max Act: 4.0089. Min Act: -0.1700

Data Index: 7230875 (Open Web Text)

Max Activating Token Index: 348

Text #13

Max Range: 4.0642. Min Range: -4.0642

Max Act: 4.0002. Min Act: -0.1700

Data Index: 2993691 (Open Web Text)

Max Activating Token Index: 851

Text #14

Max Range: 4.0642. Min Range: -4.0642

Max Act: 3.9930. Min Act: -0.1700

Data Index: 1456008 (Open Web Text)

Max Activating Token Index: 586

Text #15

Max Range: 4.0642. Min Range: -4.0642

Max Act: 3.9864. Min Act: -0.1700

Data Index: 6305161 (Open Web Text)

Max Activating Token Index: 166

Text #16

Max Range: 4.0642. Min Range: -4.0642

Max Act: 3.9954. Min Act: -0.1700

Data Index: 3719156 (Open Web Text)

Max Activating Token Index: 816

Text #17

Max Range: 4.0642. Min Range: -4.0642

Max Act: 3.9512. Min Act: -0.1700

Data Index: 1181610 (Open Web Text)

Max Activating Token Index: 563

Text #18

Max Range: 4.0642. Min Range: -4.0642

Max Act: 4.0027. Min Act: -0.1700

Data Index: 3462850 (Open Web Text)

Max Activating Token Index: 216

Text #19

Max Range: 4.0642. Min Range: -4.0642

Max Act: 3.9906. Min Act: -0.1700

Data Index: 6061382 (Open Web Text)

Max Activating Token Index: 131