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

Dataset: Open Web Text

Neuron 1432 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: 4.1811. Min Range: -4.1811

Max Act: 4.1811. Min Act: -0.1700

Data Index: 6039985 (Open Web Text)

Max Activating Token Index: 461

Text #1

Max Range: 4.1811. Min Range: -4.1811

Max Act: 4.0613. Min Act: -0.1700

Data Index: 2537640 (Open Web Text)

Max Activating Token Index: 350

Text #2

Max Range: 4.1811. Min Range: -4.1811

Max Act: 3.9846. Min Act: -0.1700

Data Index: 5593821 (Open Web Text)

Max Activating Token Index: 247

Text #3

Max Range: 4.1811. Min Range: -4.1811

Max Act: 3.9652. Min Act: -0.1700

Data Index: 4989155 (Open Web Text)

Max Activating Token Index: 998

Text #4

Max Range: 4.1811. Min Range: -4.1811

Max Act: 3.9444. Min Act: -0.1700

Data Index: 1773845 (Open Web Text)

Max Activating Token Index: 630

Text #5

Max Range: 4.1811. Min Range: -4.1811

Max Act: 3.9642. Min Act: -0.1700

Data Index: 4209414 (Open Web Text)

Max Activating Token Index: 287

Text #6

Max Range: 4.1811. Min Range: -4.1811

Max Act: 3.9133. Min Act: -0.1700

Data Index: 3782000 (Open Web Text)

Max Activating Token Index: 781

Text #7

Max Range: 4.1811. Min Range: -4.1811

Max Act: 3.9106. Min Act: -0.1700

Data Index: 1644738 (Open Web Text)

Max Activating Token Index: 756

Text #8

Max Range: 4.1811. Min Range: -4.1811

Max Act: 3.9121. Min Act: -0.1700

Data Index: 746575 (Open Web Text)

Max Activating Token Index: 22

Text #9

Max Range: 4.1811. Min Range: -4.1811

Max Act: 3.9110. Min Act: -0.1700

Data Index: 1405605 (Open Web Text)

Max Activating Token Index: 883

Text #10

Max Range: 4.1811. Min Range: -4.1811

Max Act: 3.8781. Min Act: -0.1700

Data Index: 8385106 (Open Web Text)

Max Activating Token Index: 386

Text #11

Max Range: 4.1811. Min Range: -4.1811

Max Act: 3.8996. Min Act: -0.1700

Data Index: 3637205 (Open Web Text)

Max Activating Token Index: 18

Text #12

Max Range: 4.1811. Min Range: -4.1811

Max Act: 3.8904. Min Act: -0.1700

Data Index: 8824519 (Open Web Text)

Max Activating Token Index: 298

Text #13

Max Range: 4.1811. Min Range: -4.1811

Max Act: 3.8455. Min Act: -0.1700

Data Index: 8468170 (Open Web Text)

Max Activating Token Index: 165

Text #14

Max Range: 4.1811. Min Range: -4.1811

Max Act: 3.8636. Min Act: -0.1700

Data Index: 2486251 (Open Web Text)

Max Activating Token Index: 14

Text #15

Max Range: 4.1811. Min Range: -4.1811

Max Act: 3.8182. Min Act: -0.1700

Data Index: 4595399 (Open Web Text)

Max Activating Token Index: 40

Text #16

Max Range: 4.1811. Min Range: -4.1811

Max Act: 3.8287. Min Act: -0.1700

Data Index: 8440899 (Open Web Text)

Max Activating Token Index: 19

Text #17

Max Range: 4.1811. Min Range: -4.1811

Max Act: 3.8083. Min Act: -0.1700

Data Index: 6096388 (Open Web Text)

Max Activating Token Index: 102

Text #18

Max Range: 4.1811. Min Range: -4.1811

Max Act: 3.8306. Min Act: -0.1700

Data Index: 5129267 (Open Web Text)

Max Activating Token Index: 329

Text #19

Max Range: 4.1811. Min Range: -4.1811

Max Act: 3.8034. Min Act: -0.1700

Data Index: 536657 (Open Web Text)

Max Activating Token Index: 149