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

Dataset: Open Web Text

Neuron 693 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: 4.8733. Min Range: -4.8733

Max Act: 4.8733. Min Act: -0.1700

Data Index: 7342302 (Open Web Text)

Max Activating Token Index: 586

Text #1

Max Range: 4.8733. Min Range: -4.8733

Max Act: 4.8687. Min Act: -0.1700

Data Index: 1943708 (Open Web Text)

Max Activating Token Index: 206

Text #2

Max Range: 4.8733. Min Range: -4.8733

Max Act: 4.8261. Min Act: -0.1700

Data Index: 4975193 (Open Web Text)

Max Activating Token Index: 980

Text #3

Max Range: 4.8733. Min Range: -4.8733

Max Act: 4.8483. Min Act: -0.1700

Data Index: 7328869 (Open Web Text)

Max Activating Token Index: 189

Text #4

Max Range: 4.8733. Min Range: -4.8733

Max Act: 4.8296. Min Act: -0.1700

Data Index: 6881067 (Open Web Text)

Max Activating Token Index: 901

Text #5

Max Range: 4.8733. Min Range: -4.8733

Max Act: 4.7670. Min Act: -0.1700

Data Index: 7186450 (Open Web Text)

Max Activating Token Index: 392

Text #6

Max Range: 4.8733. Min Range: -4.8733

Max Act: 4.6953. Min Act: -0.1700

Data Index: 8760000 (Open Web Text)

Max Activating Token Index: 765

Text #7

Max Range: 4.8733. Min Range: -4.8733

Max Act: 4.7047. Min Act: -0.1700

Data Index: 6448618 (Open Web Text)

Max Activating Token Index: 809

Text #8

Max Range: 4.8733. Min Range: -4.8733

Max Act: 4.7360. Min Act: -0.1700

Data Index: 4618864 (Open Web Text)

Max Activating Token Index: 17

Text #9

Max Range: 4.8733. Min Range: -4.8733

Max Act: 4.7137. Min Act: -0.1700

Data Index: 2312303 (Open Web Text)

Max Activating Token Index: 419

Text #10

Max Range: 4.8733. Min Range: -4.8733

Max Act: 4.7369. Min Act: -0.1700

Data Index: 8214811 (Open Web Text)

Max Activating Token Index: 906

Text #11

Max Range: 4.8733. Min Range: -4.8733

Max Act: 4.6981. Min Act: -0.1700

Data Index: 5818133 (Open Web Text)

Max Activating Token Index: 9

Text #12

Max Range: 4.8733. Min Range: -4.8733

Max Act: 4.7040. Min Act: -0.1700

Data Index: 2054843 (Open Web Text)

Max Activating Token Index: 1020

Text #13

Max Range: 4.8733. Min Range: -4.8733

Max Act: 4.6975. Min Act: -0.1700

Data Index: 8661969 (Open Web Text)

Max Activating Token Index: 603

Text #14

Max Range: 4.8733. Min Range: -4.8733

Max Act: 4.7298. Min Act: -0.1700

Data Index: 2800963 (Open Web Text)

Max Activating Token Index: 286

Text #15

Max Range: 4.8733. Min Range: -4.8733

Max Act: 4.7517. Min Act: -0.1700

Data Index: 7532725 (Open Web Text)

Max Activating Token Index: 1014

Text #16

Max Range: 4.8733. Min Range: -4.8733

Max Act: 4.7416. Min Act: -0.1700

Data Index: 2313802 (Open Web Text)

Max Activating Token Index: 700

Text #17

Max Range: 4.8733. Min Range: -4.8733

Max Act: 4.6764. Min Act: -0.1700

Data Index: 872152 (Open Web Text)

Max Activating Token Index: 851

Text #18

Max Range: 4.8733. Min Range: -4.8733

Max Act: 4.7573. Min Act: -0.1700

Data Index: 418499 (Open Web Text)

Max Activating Token Index: 1012

Text #19

Max Range: 4.8733. Min Range: -4.8733

Max Act: 4.6804. Min Act: -0.1700

Data Index: 1564198 (Open Web Text)

Max Activating Token Index: 249