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

Dataset: Open Web Text

Neuron 3054 in Layer 5

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: 5.6498. Min Range: -5.6498

Max Act: 5.6498. Min Act: -0.1700

Data Index: 4855305 (Open Web Text)

Max Activating Token Index: 392

Text #1

Max Range: 5.6498. Min Range: -5.6498

Max Act: 5.2326. Min Act: -0.1700

Data Index: 5706744 (Open Web Text)

Max Activating Token Index: 381

Text #2

Max Range: 5.6498. Min Range: -5.6498

Max Act: 5.1795. Min Act: -0.1700

Data Index: 4623606 (Open Web Text)

Max Activating Token Index: 813

Text #3

Max Range: 5.6498. Min Range: -5.6498

Max Act: 5.1523. Min Act: -0.1700

Data Index: 6665546 (Open Web Text)

Max Activating Token Index: 753

Text #4

Max Range: 5.6498. Min Range: -5.6498

Max Act: 5.1380. Min Act: -0.1700

Data Index: 470163 (Open Web Text)

Max Activating Token Index: 261

Text #5

Max Range: 5.6498. Min Range: -5.6498

Max Act: 5.0946. Min Act: -0.1700

Data Index: 5110060 (Open Web Text)

Max Activating Token Index: 653

Text #6

Max Range: 5.6498. Min Range: -5.6498

Max Act: 5.0815. Min Act: -0.1700

Data Index: 5470865 (Open Web Text)

Max Activating Token Index: 469

Text #7

Max Range: 5.6498. Min Range: -5.6498

Max Act: 5.0127. Min Act: -0.1700

Data Index: 2468363 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 5.6498. Min Range: -5.6498

Max Act: 5.0894. Min Act: -0.1700

Data Index: 1044573 (Open Web Text)

Max Activating Token Index: 842

Text #9

Max Range: 5.6498. Min Range: -5.6498

Max Act: 5.0537. Min Act: -0.1700

Data Index: 8148191 (Open Web Text)

Max Activating Token Index: 970

Text #10

Max Range: 5.6498. Min Range: -5.6498

Max Act: 5.0570. Min Act: -0.1700

Data Index: 1258361 (Open Web Text)

Max Activating Token Index: 273

Text #11

Max Range: 5.6498. Min Range: -5.6498

Max Act: 5.0306. Min Act: -0.1700

Data Index: 3596733 (Open Web Text)

Max Activating Token Index: 1016

Text #12

Max Range: 5.6498. Min Range: -5.6498

Max Act: 4.9911. Min Act: -0.1700

Data Index: 6548527 (Open Web Text)

Max Activating Token Index: 987

Text #13

Max Range: 5.6498. Min Range: -5.6498

Max Act: 5.0452. Min Act: -0.1700

Data Index: 4346208 (Open Web Text)

Max Activating Token Index: 912

Text #14

Max Range: 5.6498. Min Range: -5.6498

Max Act: 4.9939. Min Act: -0.1700

Data Index: 491355 (Open Web Text)

Max Activating Token Index: 313

Text #15

Max Range: 5.6498. Min Range: -5.6498

Max Act: 4.9551. Min Act: -0.1700

Data Index: 1970551 (Open Web Text)

Max Activating Token Index: 921

Text #16

Max Range: 5.6498. Min Range: -5.6498

Max Act: 5.0004. Min Act: -0.1700

Data Index: 1916996 (Open Web Text)

Max Activating Token Index: 452

Text #17

Max Range: 5.6498. Min Range: -5.6498

Max Act: 4.9501. Min Act: -0.1700

Data Index: 6122566 (Open Web Text)

Max Activating Token Index: 328

Text #18

Max Range: 5.6498. Min Range: -5.6498

Max Act: 4.9905. Min Act: -0.1700

Data Index: 8411071 (Open Web Text)

Max Activating Token Index: 270

Text #19

Max Range: 5.6498. Min Range: -5.6498

Max Act: 4.9317. Min Act: -0.1700

Data Index: 925024 (Open Web Text)

Max Activating Token Index: 524