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

Dataset: Open Web Text

Neuron 59 in Layer 3

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: 3.9318. Min Range: -3.9318

Max Act: 3.9318. Min Act: -0.1700

Data Index: 6745539 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 3.9318. Min Range: -3.9318

Max Act: 3.8807. Min Act: -0.1700

Data Index: 4058528 (Open Web Text)

Max Activating Token Index: 540

Text #2

Max Range: 3.9318. Min Range: -3.9318

Max Act: 3.8724. Min Act: -0.1700

Data Index: 970822 (Open Web Text)

Max Activating Token Index: 315

Text #3

Max Range: 3.9318. Min Range: -3.9318

Max Act: 3.8405. Min Act: -0.1700

Data Index: 1139802 (Open Web Text)

Max Activating Token Index: 350

Text #4

Max Range: 3.9318. Min Range: -3.9318

Max Act: 3.8491. Min Act: -0.1700

Data Index: 797731 (Open Web Text)

Max Activating Token Index: 164

Text #5

Max Range: 3.9318. Min Range: -3.9318

Max Act: 3.8393. Min Act: -0.1700

Data Index: 4160029 (Open Web Text)

Max Activating Token Index: 626

Text #6

Max Range: 3.9318. Min Range: -3.9318

Max Act: 3.8431. Min Act: -0.1700

Data Index: 4796039 (Open Web Text)

Max Activating Token Index: 106

Text #7

Max Range: 3.9318. Min Range: -3.9318

Max Act: 3.8535. Min Act: -0.1700

Data Index: 4225152 (Open Web Text)

Max Activating Token Index: 20

Text #8

Max Range: 3.9318. Min Range: -3.9318

Max Act: 3.8741. Min Act: -0.1700

Data Index: 5414152 (Open Web Text)

Max Activating Token Index: 130

Text #9

Max Range: 3.9318. Min Range: -3.9318

Max Act: 3.8069. Min Act: -0.1700

Data Index: 442825 (Open Web Text)

Max Activating Token Index: 118

Text #10

Max Range: 3.9318. Min Range: -3.9318

Max Act: 3.8052. Min Act: -0.1700

Data Index: 7846281 (Open Web Text)

Max Activating Token Index: 778

Text #11

Max Range: 3.9318. Min Range: -3.9318

Max Act: 3.8171. Min Act: -0.1700

Data Index: 4666569 (Open Web Text)

Max Activating Token Index: 134

Text #12

Max Range: 3.9318. Min Range: -3.9318

Max Act: 3.7761. Min Act: -0.1700

Data Index: 1154028 (Open Web Text)

Max Activating Token Index: 139

Text #13

Max Range: 3.9318. Min Range: -3.9318

Max Act: 3.7932. Min Act: -0.1700

Data Index: 4058529 (Open Web Text)

Max Activating Token Index: 462

Text #14

Max Range: 3.9318. Min Range: -3.9318

Max Act: 3.7807. Min Act: -0.1700

Data Index: 2070647 (Open Web Text)

Max Activating Token Index: 191

Text #15

Max Range: 3.9318. Min Range: -3.9318

Max Act: 3.8014. Min Act: -0.1700

Data Index: 1064266 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 3.9318. Min Range: -3.9318

Max Act: 3.7896. Min Act: -0.1700

Data Index: 7705510 (Open Web Text)

Max Activating Token Index: 525

Text #17

Max Range: 3.9318. Min Range: -3.9318

Max Act: 3.8322. Min Act: -0.1700

Data Index: 7346432 (Open Web Text)

Max Activating Token Index: 636

Text #18

Max Range: 3.9318. Min Range: -3.9318

Max Act: 3.8253. Min Act: -0.1700

Data Index: 7721445 (Open Web Text)

Max Activating Token Index: 318

Text #19

Max Range: 3.9318. Min Range: -3.9318

Max Act: 3.7277. Min Act: -0.1700

Data Index: 8009939 (Open Web Text)

Max Activating Token Index: 426