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

Dataset: Open Web Text

Neuron 432 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: 3.0752. Min Range: -3.0752

Max Act: 3.0672. Min Act: -0.1700

Data Index: 3331436 (Open Web Text)

Max Activating Token Index: 843

Text #1

Max Range: 3.0752. Min Range: -3.0752

Max Act: 3.0752. Min Act: -0.1700

Data Index: 6185589 (Open Web Text)

Max Activating Token Index: 429

Text #2

Max Range: 3.0752. Min Range: -3.0752

Max Act: 3.0591. Min Act: -0.1700

Data Index: 1505697 (Open Web Text)

Max Activating Token Index: 188

Text #3

Max Range: 3.0752. Min Range: -3.0752

Max Act: 3.0677. Min Act: -0.1700

Data Index: 7646333 (Open Web Text)

Max Activating Token Index: 312

Text #4

Max Range: 3.0752. Min Range: -3.0752

Max Act: 3.0051. Min Act: -0.1700

Data Index: 8824920 (Open Web Text)

Max Activating Token Index: 203

Text #5

Max Range: 3.0752. Min Range: -3.0752

Max Act: 3.0070. Min Act: -0.1700

Data Index: 4163415 (Open Web Text)

Max Activating Token Index: 808

Text #6

Max Range: 3.0752. Min Range: -3.0752

Max Act: 3.0084. Min Act: -0.1700

Data Index: 4221235 (Open Web Text)

Max Activating Token Index: 294

Text #7

Max Range: 3.0752. Min Range: -3.0752

Max Act: 2.9439. Min Act: -0.1700

Data Index: 5000004 (Open Web Text)

Max Activating Token Index: 262

Text #8

Max Range: 3.0752. Min Range: -3.0752

Max Act: 2.9513. Min Act: -0.1700

Data Index: 7284344 (Open Web Text)

Max Activating Token Index: 508

Text #9

Max Range: 3.0752. Min Range: -3.0752

Max Act: 2.9360. Min Act: -0.1700

Data Index: 3799398 (Open Web Text)

Max Activating Token Index: 770

Text #10

Max Range: 3.0752. Min Range: -3.0752

Max Act: 2.9493. Min Act: -0.1700

Data Index: 1551791 (Open Web Text)

Max Activating Token Index: 18

Text #11

Max Range: 3.0752. Min Range: -3.0752

Max Act: 2.9401. Min Act: -0.1700

Data Index: 5123070 (Open Web Text)

Max Activating Token Index: 573

Text #12

Max Range: 3.0752. Min Range: -3.0752

Max Act: 2.9211. Min Act: -0.1700

Data Index: 5597459 (Open Web Text)

Max Activating Token Index: 196

Text #13

Max Range: 3.0752. Min Range: -3.0752

Max Act: 2.9216. Min Act: -0.1700

Data Index: 5952863 (Open Web Text)

Max Activating Token Index: 920

Text #14

Max Range: 3.0752. Min Range: -3.0752

Max Act: 2.9062. Min Act: -0.1700

Data Index: 651239 (Open Web Text)

Max Activating Token Index: 33

Text #15

Max Range: 3.0752. Min Range: -3.0752

Max Act: 2.8878. Min Act: -0.1700

Data Index: 5166800 (Open Web Text)

Max Activating Token Index: 673

Text #16

Max Range: 3.0752. Min Range: -3.0752

Max Act: 2.9098. Min Act: -0.1700

Data Index: 3433250 (Open Web Text)

Max Activating Token Index: 353

Text #17

Max Range: 3.0752. Min Range: -3.0752

Max Act: 2.9149. Min Act: -0.1700

Data Index: 3749150 (Open Web Text)

Max Activating Token Index: 129

Text #18

Max Range: 3.0752. Min Range: -3.0752

Max Act: 2.9002. Min Act: -0.1700

Data Index: 1732348 (Open Web Text)

Max Activating Token Index: 114

Text #19

Max Range: 3.0752. Min Range: -3.0752

Max Act: 2.9248. Min Act: -0.1700

Data Index: 587667 (Open Web Text)

Max Activating Token Index: 805