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

Dataset: Open Web Text

Neuron 480 in Layer 1

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: 1.8541. Min Range: -1.8541

Max Act: 1.8541. Min Act: -0.1696

Data Index: 3704801 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.8233. Min Act: -0.1700

Data Index: 8636444 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.7964. Min Act: -0.1700

Data Index: 2837329 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.8138. Min Act: -0.1699

Data Index: 8407705 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.7822. Min Act: -0.1700

Data Index: 334861 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.7857. Min Act: -0.1698

Data Index: 1067635 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.7883. Min Act: -0.1700

Data Index: 4070660 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.7931. Min Act: -0.1700

Data Index: 6126348 (Open Web Text)

Max Activating Token Index: 9

Text #8

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.7877. Min Act: -0.1700

Data Index: 3998611 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.7823. Min Act: -0.1700

Data Index: 6284495 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.7650. Min Act: -0.1700

Data Index: 6914681 (Open Web Text)

Max Activating Token Index: 9

Text #11

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.7765. Min Act: -0.1697

Data Index: 6027977 (Open Web Text)

Max Activating Token Index: 429

Text #12

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.7670. Min Act: -0.1700

Data Index: 795550 (Open Web Text)

Max Activating Token Index: 10

Text #13

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.7688. Min Act: -0.1698

Data Index: 1600485 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.7572. Min Act: -0.1700

Data Index: 3896357 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.7654. Min Act: -0.1700

Data Index: 5251231 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.7552. Min Act: -0.1700

Data Index: 1267021 (Open Web Text)

Max Activating Token Index: 181

Text #17

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.7563. Min Act: -0.1698

Data Index: 2462348 (Open Web Text)

Max Activating Token Index: 10

Text #18

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.7578. Min Act: -0.1699

Data Index: 8822491 (Open Web Text)

Max Activating Token Index: 135

Text #19

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.7490. Min Act: -0.1700

Data Index: 3094050 (Open Web Text)

Max Activating Token Index: 4