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

Dataset: Open Web Text

Neuron 2809 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: 2.0018. Min Range: -2.0018

Max Act: 2.0018. Min Act: -0.1700

Data Index: 4037530 (Open Web Text)

Max Activating Token Index: 736

Text #1

Max Range: 2.0018. Min Range: -2.0018

Max Act: 1.9897. Min Act: -0.1700

Data Index: 6643201 (Open Web Text)

Max Activating Token Index: 136

Text #2

Max Range: 2.0018. Min Range: -2.0018

Max Act: 1.9469. Min Act: -0.1700

Data Index: 8373679 (Open Web Text)

Max Activating Token Index: 541

Text #3

Max Range: 2.0018. Min Range: -2.0018

Max Act: 1.9226. Min Act: -0.1700

Data Index: 359920 (Open Web Text)

Max Activating Token Index: 123

Text #4

Max Range: 2.0018. Min Range: -2.0018

Max Act: 1.9128. Min Act: -0.1699

Data Index: 7349221 (Open Web Text)

Max Activating Token Index: 95

Text #5

Max Range: 2.0018. Min Range: -2.0018

Max Act: 1.9124. Min Act: -0.1700

Data Index: 8826734 (Open Web Text)

Max Activating Token Index: 33

Text #6

Max Range: 2.0018. Min Range: -2.0018

Max Act: 1.8990. Min Act: -0.1700

Data Index: 3904027 (Open Web Text)

Max Activating Token Index: 670

Text #7

Max Range: 2.0018. Min Range: -2.0018

Max Act: 1.8997. Min Act: -0.1700

Data Index: 267333 (Open Web Text)

Max Activating Token Index: 238

Text #8

Max Range: 2.0018. Min Range: -2.0018

Max Act: 1.8910. Min Act: -0.1700

Data Index: 5114387 (Open Web Text)

Max Activating Token Index: 122

Text #9

Max Range: 2.0018. Min Range: -2.0018

Max Act: 1.8923. Min Act: -0.1700

Data Index: 1394317 (Open Web Text)

Max Activating Token Index: 60

Text #10

Max Range: 2.0018. Min Range: -2.0018

Max Act: 1.8868. Min Act: -0.1700

Data Index: 8472015 (Open Web Text)

Max Activating Token Index: 132

Text #11

Max Range: 2.0018. Min Range: -2.0018

Max Act: 1.8816. Min Act: -0.1699

Data Index: 6066168 (Open Web Text)

Max Activating Token Index: 449

Text #12

Max Range: 2.0018. Min Range: -2.0018

Max Act: 1.8753. Min Act: -0.1700

Data Index: 4484970 (Open Web Text)

Max Activating Token Index: 139

Text #13

Max Range: 2.0018. Min Range: -2.0018

Max Act: 1.8781. Min Act: -0.1252

Data Index: 8288092 (Open Web Text)

Max Activating Token Index: 395

Text #14

Max Range: 2.0018. Min Range: -2.0018

Max Act: 1.8790. Min Act: -0.1700

Data Index: 3285001 (Open Web Text)

Max Activating Token Index: 419

Text #15

Max Range: 2.0018. Min Range: -2.0018

Max Act: 1.8752. Min Act: -0.1700

Data Index: 6284139 (Open Web Text)

Max Activating Token Index: 643

Text #16

Max Range: 2.0018. Min Range: -2.0018

Max Act: 1.8604. Min Act: -0.1700

Data Index: 6932709 (Open Web Text)

Max Activating Token Index: 145

Text #17

Max Range: 2.0018. Min Range: -2.0018

Max Act: 1.8637. Min Act: -0.1700

Data Index: 1353390 (Open Web Text)

Max Activating Token Index: 257

Text #18

Max Range: 2.0018. Min Range: -2.0018

Max Act: 1.8604. Min Act: -0.1700

Data Index: 3598360 (Open Web Text)

Max Activating Token Index: 479

Text #19

Max Range: 2.0018. Min Range: -2.0018

Max Act: 1.8600. Min Act: -0.1700

Data Index: 5381715 (Open Web Text)

Max Activating Token Index: 460