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

Dataset: Open Web Text

Neuron 334 in Layer 4

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: 4.3004. Min Range: -4.3004

Max Act: 4.3004. Min Act: -0.1700

Data Index: 4413718 (Open Web Text)

Max Activating Token Index: 858

Text #1

Max Range: 4.3004. Min Range: -4.3004

Max Act: 4.1488. Min Act: -0.1700

Data Index: 7543840 (Open Web Text)

Max Activating Token Index: 28

Text #2

Max Range: 4.3004. Min Range: -4.3004

Max Act: 4.1423. Min Act: -0.1700

Data Index: 5398350 (Open Web Text)

Max Activating Token Index: 875

Text #3

Max Range: 4.3004. Min Range: -4.3004

Max Act: 4.0639. Min Act: -0.1700

Data Index: 5309322 (Open Web Text)

Max Activating Token Index: 630

Text #4

Max Range: 4.3004. Min Range: -4.3004

Max Act: 4.0679. Min Act: -0.1700

Data Index: 5398351 (Open Web Text)

Max Activating Token Index: 33

Text #5

Max Range: 4.3004. Min Range: -4.3004

Max Act: 4.0291. Min Act: -0.1700

Data Index: 7836685 (Open Web Text)

Max Activating Token Index: 518

Text #6

Max Range: 4.3004. Min Range: -4.3004

Max Act: 3.9894. Min Act: -0.1700

Data Index: 7152129 (Open Web Text)

Max Activating Token Index: 381

Text #7

Max Range: 4.3004. Min Range: -4.3004

Max Act: 3.9798. Min Act: -0.1700

Data Index: 706609 (Open Web Text)

Max Activating Token Index: 28

Text #8

Max Range: 4.3004. Min Range: -4.3004

Max Act: 4.0109. Min Act: -0.1700

Data Index: 1356538 (Open Web Text)

Max Activating Token Index: 169

Text #9

Max Range: 4.3004. Min Range: -4.3004

Max Act: 4.0102. Min Act: -0.1700

Data Index: 2894663 (Open Web Text)

Max Activating Token Index: 792

Text #10

Max Range: 4.3004. Min Range: -4.3004

Max Act: 3.9822. Min Act: -0.1700

Data Index: 7425550 (Open Web Text)

Max Activating Token Index: 574

Text #11

Max Range: 4.3004. Min Range: -4.3004

Max Act: 3.9956. Min Act: -0.1700

Data Index: 7796172 (Open Web Text)

Max Activating Token Index: 156

Text #12

Max Range: 4.3004. Min Range: -4.3004

Max Act: 4.0068. Min Act: -0.1700

Data Index: 6881349 (Open Web Text)

Max Activating Token Index: 654

Text #13

Max Range: 4.3004. Min Range: -4.3004

Max Act: 4.0207. Min Act: -0.1700

Data Index: 8311483 (Open Web Text)

Max Activating Token Index: 987

Text #14

Max Range: 4.3004. Min Range: -4.3004

Max Act: 3.9918. Min Act: -0.1700

Data Index: 883298 (Open Web Text)

Max Activating Token Index: 527

Text #15

Max Range: 4.3004. Min Range: -4.3004

Max Act: 3.9258. Min Act: -0.1700

Data Index: 2195356 (Open Web Text)

Max Activating Token Index: 15

Text #16

Max Range: 4.3004. Min Range: -4.3004

Max Act: 3.9122. Min Act: -0.1700

Data Index: 1262935 (Open Web Text)

Max Activating Token Index: 990

Text #17

Max Range: 4.3004. Min Range: -4.3004

Max Act: 3.9541. Min Act: -0.1700

Data Index: 7688266 (Open Web Text)

Max Activating Token Index: 221

Text #18

Max Range: 4.3004. Min Range: -4.3004

Max Act: 3.9360. Min Act: -0.1700

Data Index: 7796179 (Open Web Text)

Max Activating Token Index: 22

Text #19

Max Range: 4.3004. Min Range: -4.3004

Max Act: 3.9072. Min Act: -0.1700

Data Index: 6017268 (Open Web Text)

Max Activating Token Index: 710