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

Dataset: Open Web Text

Neuron 1332 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: 3.1701. Min Range: -3.1701

Max Act: 3.1594. Min Act: -0.1700

Data Index: 1958628 (Open Web Text)

Max Activating Token Index: 441

Text #1

Max Range: 3.1701. Min Range: -3.1701

Max Act: 3.1701. Min Act: -0.1700

Data Index: 1334319 (Open Web Text)

Max Activating Token Index: 557

Text #2

Max Range: 3.1701. Min Range: -3.1701

Max Act: 3.1268. Min Act: -0.1700

Data Index: 2031384 (Open Web Text)

Max Activating Token Index: 472

Text #3

Max Range: 3.1701. Min Range: -3.1701

Max Act: 3.0666. Min Act: -0.1700

Data Index: 5653561 (Open Web Text)

Max Activating Token Index: 775

Text #4

Max Range: 3.1701. Min Range: -3.1701

Max Act: 3.0699. Min Act: -0.1700

Data Index: 8083322 (Open Web Text)

Max Activating Token Index: 67

Text #5

Max Range: 3.1701. Min Range: -3.1701

Max Act: 3.0739. Min Act: -0.1700

Data Index: 3519985 (Open Web Text)

Max Activating Token Index: 807

Text #6

Max Range: 3.1701. Min Range: -3.1701

Max Act: 3.0837. Min Act: -0.1700

Data Index: 4976822 (Open Web Text)

Max Activating Token Index: 547

Text #7

Max Range: 3.1701. Min Range: -3.1701

Max Act: 3.0410. Min Act: -0.1700

Data Index: 6975859 (Open Web Text)

Max Activating Token Index: 494

Text #8

Max Range: 3.1701. Min Range: -3.1701

Max Act: 3.0355. Min Act: -0.1700

Data Index: 4527752 (Open Web Text)

Max Activating Token Index: 694

Text #9

Max Range: 3.1701. Min Range: -3.1701

Max Act: 3.0310. Min Act: -0.1700

Data Index: 2377782 (Open Web Text)

Max Activating Token Index: 1011

Text #10

Max Range: 3.1701. Min Range: -3.1701

Max Act: 3.0279. Min Act: -0.1700

Data Index: 4909834 (Open Web Text)

Max Activating Token Index: 60

Text #11

Max Range: 3.1701. Min Range: -3.1701

Max Act: 3.0110. Min Act: -0.1700

Data Index: 3712091 (Open Web Text)

Max Activating Token Index: 520

Text #12

Max Range: 3.1701. Min Range: -3.1701

Max Act: 3.0317. Min Act: -0.1700

Data Index: 8722125 (Open Web Text)

Max Activating Token Index: 954

Text #13

Max Range: 3.1701. Min Range: -3.1701

Max Act: 3.0171. Min Act: -0.1700

Data Index: 2679430 (Open Web Text)

Max Activating Token Index: 194

Text #14

Max Range: 3.1701. Min Range: -3.1701

Max Act: 3.0127. Min Act: -0.1700

Data Index: 5220185 (Open Web Text)

Max Activating Token Index: 96

Text #15

Max Range: 3.1701. Min Range: -3.1701

Max Act: 3.0119. Min Act: -0.1700

Data Index: 602530 (Open Web Text)

Max Activating Token Index: 413

Text #16

Max Range: 3.1701. Min Range: -3.1701

Max Act: 3.0031. Min Act: -0.1700

Data Index: 4026644 (Open Web Text)

Max Activating Token Index: 409

Text #17

Max Range: 3.1701. Min Range: -3.1701

Max Act: 3.0139. Min Act: -0.1700

Data Index: 7894515 (Open Web Text)

Max Activating Token Index: 599

Text #18

Max Range: 3.1701. Min Range: -3.1701

Max Act: 3.0088. Min Act: -0.1700

Data Index: 1958629 (Open Web Text)

Max Activating Token Index: 412

Text #19

Max Range: 3.1701. Min Range: -3.1701

Max Act: 3.0058. Min Act: -0.1700

Data Index: 8083321 (Open Web Text)

Max Activating Token Index: 175