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

Dataset: Open Web Text

Neuron 191 in Layer 5

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: 3.7901. Min Range: -3.7901

Max Act: 3.7901. Min Act: -0.1700

Data Index: 1705948 (Open Web Text)

Max Activating Token Index: 216

Text #1

Max Range: 3.7901. Min Range: -3.7901

Max Act: 3.7428. Min Act: -0.1700

Data Index: 8243010 (Open Web Text)

Max Activating Token Index: 631

Text #2

Max Range: 3.7901. Min Range: -3.7901

Max Act: 3.7705. Min Act: -0.1700

Data Index: 5086805 (Open Web Text)

Max Activating Token Index: 356

Text #3

Max Range: 3.7901. Min Range: -3.7901

Max Act: 3.6637. Min Act: -0.1700

Data Index: 7615963 (Open Web Text)

Max Activating Token Index: 106

Text #4

Max Range: 3.7901. Min Range: -3.7901

Max Act: 3.6450. Min Act: -0.1700

Data Index: 4720975 (Open Web Text)

Max Activating Token Index: 775

Text #5

Max Range: 3.7901. Min Range: -3.7901

Max Act: 3.5706. Min Act: -0.1700

Data Index: 8398142 (Open Web Text)

Max Activating Token Index: 243

Text #6

Max Range: 3.7901. Min Range: -3.7901

Max Act: 3.5717. Min Act: -0.1700

Data Index: 1202775 (Open Web Text)

Max Activating Token Index: 777

Text #7

Max Range: 3.7901. Min Range: -3.7901

Max Act: 3.5006. Min Act: -0.1700

Data Index: 8246739 (Open Web Text)

Max Activating Token Index: 691

Text #8

Max Range: 3.7901. Min Range: -3.7901

Max Act: 3.4802. Min Act: -0.1700

Data Index: 1977721 (Open Web Text)

Max Activating Token Index: 366

Text #9

Max Range: 3.7901. Min Range: -3.7901

Max Act: 3.5139. Min Act: -0.1700

Data Index: 6051628 (Open Web Text)

Max Activating Token Index: 992

Text #10

Max Range: 3.7901. Min Range: -3.7901

Max Act: 3.5047. Min Act: -0.1700

Data Index: 557664 (Open Web Text)

Max Activating Token Index: 200

Text #11

Max Range: 3.7901. Min Range: -3.7901

Max Act: 3.4985. Min Act: -0.1700

Data Index: 5523388 (Open Web Text)

Max Activating Token Index: 855

Text #12

Max Range: 3.7901. Min Range: -3.7901

Max Act: 3.4970. Min Act: -0.1700

Data Index: 2438661 (Open Web Text)

Max Activating Token Index: 217

Text #13

Max Range: 3.7901. Min Range: -3.7901

Max Act: 3.4709. Min Act: -0.1700

Data Index: 4183560 (Open Web Text)

Max Activating Token Index: 58

Text #14

Max Range: 3.7901. Min Range: -3.7901

Max Act: 3.4779. Min Act: -0.1700

Data Index: 8710029 (Open Web Text)

Max Activating Token Index: 756

Text #15

Max Range: 3.7901. Min Range: -3.7901

Max Act: 3.4789. Min Act: -0.1700

Data Index: 1563156 (Open Web Text)

Max Activating Token Index: 201

Text #16

Max Range: 3.7901. Min Range: -3.7901

Max Act: 3.4447. Min Act: -0.1700

Data Index: 6825775 (Open Web Text)

Max Activating Token Index: 65

Text #17

Max Range: 3.7901. Min Range: -3.7901

Max Act: 3.4533. Min Act: -0.1700

Data Index: 1540431 (Open Web Text)

Max Activating Token Index: 224

Text #18

Max Range: 3.7901. Min Range: -3.7901

Max Act: 3.4729. Min Act: -0.1700

Data Index: 6311073 (Open Web Text)

Max Activating Token Index: 994

Text #19

Max Range: 3.7901. Min Range: -3.7901

Max Act: 3.4294. Min Act: -0.1700

Data Index: 5503842 (Open Web Text)

Max Activating Token Index: 134