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

Dataset: Open Web Text

Neuron 23 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: 1.7062. Min Range: -1.7062

Max Act: 1.7036. Min Act: -0.1700

Data Index: 1750074 (Open Web Text)

Max Activating Token Index: 208

Text #1

Max Range: 1.7062. Min Range: -1.7062

Max Act: 1.7062. Min Act: -0.1700

Data Index: 8231436 (Open Web Text)

Max Activating Token Index: 93

Text #2

Max Range: 1.7062. Min Range: -1.7062

Max Act: 1.6865. Min Act: -0.1700

Data Index: 6332108 (Open Web Text)

Max Activating Token Index: 680

Text #3

Max Range: 1.7062. Min Range: -1.7062

Max Act: 1.6978. Min Act: -0.1700

Data Index: 3921472 (Open Web Text)

Max Activating Token Index: 944

Text #4

Max Range: 1.7062. Min Range: -1.7062

Max Act: 1.6956. Min Act: -0.1700

Data Index: 1728776 (Open Web Text)

Max Activating Token Index: 124

Text #5

Max Range: 1.7062. Min Range: -1.7062

Max Act: 1.6718. Min Act: -0.1700

Data Index: 5218490 (Open Web Text)

Max Activating Token Index: 113

Text #6

Max Range: 1.7062. Min Range: -1.7062

Max Act: 1.6625. Min Act: -0.1700

Data Index: 2404615 (Open Web Text)

Max Activating Token Index: 288

Text #7

Max Range: 1.7062. Min Range: -1.7062

Max Act: 1.6794. Min Act: -0.1700

Data Index: 488615 (Open Web Text)

Max Activating Token Index: 676

Text #8

Max Range: 1.7062. Min Range: -1.7062

Max Act: 1.6644. Min Act: -0.1700

Data Index: 4332296 (Open Web Text)

Max Activating Token Index: 82

Text #9

Max Range: 1.7062. Min Range: -1.7062

Max Act: 1.6679. Min Act: -0.1700

Data Index: 1672308 (Open Web Text)

Max Activating Token Index: 458

Text #10

Max Range: 1.7062. Min Range: -1.7062

Max Act: 1.6499. Min Act: -0.1700

Data Index: 2656368 (Open Web Text)

Max Activating Token Index: 506

Text #11

Max Range: 1.7062. Min Range: -1.7062

Max Act: 1.6396. Min Act: -0.1700

Data Index: 7369444 (Open Web Text)

Max Activating Token Index: 422

Text #12

Max Range: 1.7062. Min Range: -1.7062

Max Act: 1.6425. Min Act: -0.1700

Data Index: 1797935 (Open Web Text)

Max Activating Token Index: 461

Text #13

Max Range: 1.7062. Min Range: -1.7062

Max Act: 1.6474. Min Act: -0.1700

Data Index: 7634612 (Open Web Text)

Max Activating Token Index: 640

Text #14

Max Range: 1.7062. Min Range: -1.7062

Max Act: 1.6456. Min Act: -0.1700

Data Index: 2516386 (Open Web Text)

Max Activating Token Index: 276

Text #15

Max Range: 1.7062. Min Range: -1.7062

Max Act: 1.6441. Min Act: -0.1700

Data Index: 1262513 (Open Web Text)

Max Activating Token Index: 810

Text #16

Max Range: 1.7062. Min Range: -1.7062

Max Act: 1.6281. Min Act: -0.1700

Data Index: 5345365 (Open Web Text)

Max Activating Token Index: 147

Text #17

Max Range: 1.7062. Min Range: -1.7062

Max Act: 1.6404. Min Act: -0.1700

Data Index: 5376308 (Open Web Text)

Max Activating Token Index: 389

Text #18

Max Range: 1.7062. Min Range: -1.7062

Max Act: 1.6332. Min Act: -0.1700

Data Index: 5431827 (Open Web Text)

Max Activating Token Index: 129

Text #19

Max Range: 1.7062. Min Range: -1.7062

Max Act: 1.6311. Min Act: -0.1700

Data Index: 1750080 (Open Web Text)

Max Activating Token Index: 127