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

Dataset: Open Web Text

Neuron 1646 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: 4.0827. Min Range: -4.0827

Max Act: 4.0827. Min Act: -0.1700

Data Index: 6103602 (Open Web Text)

Max Activating Token Index: 237

Text #1

Max Range: 4.0827. Min Range: -4.0827

Max Act: 4.0691. Min Act: -0.1700

Data Index: 3456652 (Open Web Text)

Max Activating Token Index: 594

Text #2

Max Range: 4.0827. Min Range: -4.0827

Max Act: 4.0106. Min Act: -0.1700

Data Index: 5685161 (Open Web Text)

Max Activating Token Index: 459

Text #3

Max Range: 4.0827. Min Range: -4.0827

Max Act: 4.0158. Min Act: -0.1700

Data Index: 8080883 (Open Web Text)

Max Activating Token Index: 175

Text #4

Max Range: 4.0827. Min Range: -4.0827

Max Act: 3.9973. Min Act: -0.1700

Data Index: 7698094 (Open Web Text)

Max Activating Token Index: 525

Text #5

Max Range: 4.0827. Min Range: -4.0827

Max Act: 3.9933. Min Act: -0.1700

Data Index: 5752538 (Open Web Text)

Max Activating Token Index: 124

Text #6

Max Range: 4.0827. Min Range: -4.0827

Max Act: 4.0118. Min Act: -0.1700

Data Index: 446327 (Open Web Text)

Max Activating Token Index: 177

Text #7

Max Range: 4.0827. Min Range: -4.0827

Max Act: 3.9924. Min Act: -0.1700

Data Index: 2574522 (Open Web Text)

Max Activating Token Index: 795

Text #8

Max Range: 4.0827. Min Range: -4.0827

Max Act: 3.9641. Min Act: -0.1700

Data Index: 2630033 (Open Web Text)

Max Activating Token Index: 87

Text #9

Max Range: 4.0827. Min Range: -4.0827

Max Act: 3.9707. Min Act: -0.1700

Data Index: 4869209 (Open Web Text)

Max Activating Token Index: 1006

Text #10

Max Range: 4.0827. Min Range: -4.0827

Max Act: 3.9802. Min Act: -0.1700

Data Index: 1309432 (Open Web Text)

Max Activating Token Index: 676

Text #11

Max Range: 4.0827. Min Range: -4.0827

Max Act: 3.9639. Min Act: -0.1700

Data Index: 5006402 (Open Web Text)

Max Activating Token Index: 727

Text #12

Max Range: 4.0827. Min Range: -4.0827

Max Act: 3.9666. Min Act: -0.1700

Data Index: 3812848 (Open Web Text)

Max Activating Token Index: 341

Text #13

Max Range: 4.0827. Min Range: -4.0827

Max Act: 3.9820. Min Act: -0.1700

Data Index: 5693158 (Open Web Text)

Max Activating Token Index: 384

Text #14

Max Range: 4.0827. Min Range: -4.0827

Max Act: 3.9670. Min Act: -0.1700

Data Index: 1270369 (Open Web Text)

Max Activating Token Index: 741

Text #15

Max Range: 4.0827. Min Range: -4.0827

Max Act: 3.9779. Min Act: -0.1700

Data Index: 575281 (Open Web Text)

Max Activating Token Index: 553

Text #16

Max Range: 4.0827. Min Range: -4.0827

Max Act: 3.9867. Min Act: -0.1700

Data Index: 695232 (Open Web Text)

Max Activating Token Index: 110

Text #17

Max Range: 4.0827. Min Range: -4.0827

Max Act: 3.9610. Min Act: -0.1700

Data Index: 45765 (Open Web Text)

Max Activating Token Index: 123

Text #18

Max Range: 4.0827. Min Range: -4.0827

Max Act: 3.9808. Min Act: -0.1700

Data Index: 4460453 (Open Web Text)

Max Activating Token Index: 150

Text #19

Max Range: 4.0827. Min Range: -4.0827

Max Act: 3.9507. Min Act: -0.1700

Data Index: 4105563 (Open Web Text)

Max Activating Token Index: 366