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

Dataset: Open Web Text

Neuron 1994 in Layer 6

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: 3.7343. Min Range: -3.7343

Max Act: 3.7106. Min Act: -0.1700

Data Index: 3059682 (Open Web Text)

Max Activating Token Index: 48

Text #1

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.7343. Min Act: -0.1700

Data Index: 7436862 (Open Web Text)

Max Activating Token Index: 419

Text #2

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.7281. Min Act: -0.1700

Data Index: 8803621 (Open Web Text)

Max Activating Token Index: 533

Text #3

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.7033. Min Act: -0.1700

Data Index: 2439104 (Open Web Text)

Max Activating Token Index: 961

Text #4

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.6775. Min Act: -0.1700

Data Index: 4565008 (Open Web Text)

Max Activating Token Index: 838

Text #5

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.6500. Min Act: -0.1700

Data Index: 6272082 (Open Web Text)

Max Activating Token Index: 713

Text #6

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.6590. Min Act: -0.1700

Data Index: 3424077 (Open Web Text)

Max Activating Token Index: 108

Text #7

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.6365. Min Act: -0.1700

Data Index: 2577188 (Open Web Text)

Max Activating Token Index: 514

Text #8

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.6311. Min Act: -0.1700

Data Index: 5487865 (Open Web Text)

Max Activating Token Index: 1020

Text #9

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.5668. Min Act: -0.1700

Data Index: 5880098 (Open Web Text)

Max Activating Token Index: 791

Text #10

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.5654. Min Act: -0.1700

Data Index: 8290700 (Open Web Text)

Max Activating Token Index: 944

Text #11

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.5552. Min Act: -0.1700

Data Index: 4835225 (Open Web Text)

Max Activating Token Index: 191

Text #12

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.5450. Min Act: -0.1700

Data Index: 6503684 (Open Web Text)

Max Activating Token Index: 717

Text #13

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.5628. Min Act: -0.1700

Data Index: 5674468 (Open Web Text)

Max Activating Token Index: 981

Text #14

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.5100. Min Act: -0.1700

Data Index: 6356915 (Open Web Text)

Max Activating Token Index: 370

Text #15

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.5244. Min Act: -0.1700

Data Index: 926692 (Open Web Text)

Max Activating Token Index: 980

Text #16

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.5770. Min Act: -0.1700

Data Index: 5116757 (Open Web Text)

Max Activating Token Index: 217

Text #17

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.5080. Min Act: -0.1700

Data Index: 6689145 (Open Web Text)

Max Activating Token Index: 1003

Text #18

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.5398. Min Act: -0.1700

Data Index: 7834337 (Open Web Text)

Max Activating Token Index: 629

Text #19

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.5231. Min Act: -0.1700

Data Index: 914854 (Open Web Text)

Max Activating Token Index: 505