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

Dataset: Open Web Text

Neuron 2294 in Layer 4

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: 3.1839. Min Range: -3.1839

Max Act: 3.1839. Min Act: -0.1700

Data Index: 7478445 (Open Web Text)

Max Activating Token Index: 253

Text #1

Max Range: 3.1839. Min Range: -3.1839

Max Act: 3.1487. Min Act: -0.1700

Data Index: 3373740 (Open Web Text)

Max Activating Token Index: 419

Text #2

Max Range: 3.1839. Min Range: -3.1839

Max Act: 3.0848. Min Act: -0.1700

Data Index: 2863575 (Open Web Text)

Max Activating Token Index: 216

Text #3

Max Range: 3.1839. Min Range: -3.1839

Max Act: 3.0790. Min Act: -0.1700

Data Index: 5847771 (Open Web Text)

Max Activating Token Index: 324

Text #4

Max Range: 3.1839. Min Range: -3.1839

Max Act: 3.0427. Min Act: -0.1700

Data Index: 1471058 (Open Web Text)

Max Activating Token Index: 172

Text #5

Max Range: 3.1839. Min Range: -3.1839

Max Act: 3.0368. Min Act: -0.1700

Data Index: 5429054 (Open Web Text)

Max Activating Token Index: 978

Text #6

Max Range: 3.1839. Min Range: -3.1839

Max Act: 3.0329. Min Act: -0.1700

Data Index: 7216229 (Open Web Text)

Max Activating Token Index: 205

Text #7

Max Range: 3.1839. Min Range: -3.1839

Max Act: 3.0380. Min Act: -0.1700

Data Index: 2378220 (Open Web Text)

Max Activating Token Index: 496

Text #8

Max Range: 3.1839. Min Range: -3.1839

Max Act: 3.0129. Min Act: -0.1700

Data Index: 2463684 (Open Web Text)

Max Activating Token Index: 376

Text #9

Max Range: 3.1839. Min Range: -3.1839

Max Act: 3.0360. Min Act: -0.1700

Data Index: 1139220 (Open Web Text)

Max Activating Token Index: 499

Text #10

Max Range: 3.1839. Min Range: -3.1839

Max Act: 3.0195. Min Act: -0.1700

Data Index: 1898315 (Open Web Text)

Max Activating Token Index: 338

Text #11

Max Range: 3.1839. Min Range: -3.1839

Max Act: 3.0078. Min Act: -0.1700

Data Index: 3801255 (Open Web Text)

Max Activating Token Index: 273

Text #12

Max Range: 3.1839. Min Range: -3.1839

Max Act: 3.0020. Min Act: -0.1700

Data Index: 1505813 (Open Web Text)

Max Activating Token Index: 851

Text #13

Max Range: 3.1839. Min Range: -3.1839

Max Act: 3.0236. Min Act: -0.1700

Data Index: 8063235 (Open Web Text)

Max Activating Token Index: 78

Text #14

Max Range: 3.1839. Min Range: -3.1839

Max Act: 3.0107. Min Act: -0.1700

Data Index: 1842271 (Open Web Text)

Max Activating Token Index: 499

Text #15

Max Range: 3.1839. Min Range: -3.1839

Max Act: 2.9976. Min Act: -0.1700

Data Index: 3370341 (Open Web Text)

Max Activating Token Index: 112

Text #16

Max Range: 3.1839. Min Range: -3.1839

Max Act: 3.0180. Min Act: -0.1700

Data Index: 1810774 (Open Web Text)

Max Activating Token Index: 547

Text #17

Max Range: 3.1839. Min Range: -3.1839

Max Act: 2.9927. Min Act: -0.1700

Data Index: 2321168 (Open Web Text)

Max Activating Token Index: 268

Text #18

Max Range: 3.1839. Min Range: -3.1839

Max Act: 3.0024. Min Act: -0.1700

Data Index: 5895340 (Open Web Text)

Max Activating Token Index: 374

Text #19

Max Range: 3.1839. Min Range: -3.1839

Max Act: 2.9716. Min Act: -0.1700

Data Index: 4602385 (Open Web Text)

Max Activating Token Index: 569