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

Dataset: Open Web Text

Neuron 2880 in Layer 1

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: 3.9631. Min Range: -3.9631

Max Act: 3.9631. Min Act: -0.1700

Data Index: 5665288 (Open Web Text)

Max Activating Token Index: 207

Text #1

Max Range: 3.9631. Min Range: -3.9631

Max Act: 3.9060. Min Act: -0.1700

Data Index: 5131142 (Open Web Text)

Max Activating Token Index: 852

Text #2

Max Range: 3.9631. Min Range: -3.9631

Max Act: 3.8818. Min Act: -0.1700

Data Index: 57299 (Open Web Text)

Max Activating Token Index: 119

Text #3

Max Range: 3.9631. Min Range: -3.9631

Max Act: 3.8387. Min Act: -0.1700

Data Index: 2103175 (Open Web Text)

Max Activating Token Index: 376

Text #4

Max Range: 3.9631. Min Range: -3.9631

Max Act: 3.8525. Min Act: -0.1700

Data Index: 3495574 (Open Web Text)

Max Activating Token Index: 772

Text #5

Max Range: 3.9631. Min Range: -3.9631

Max Act: 3.8212. Min Act: -0.1700

Data Index: 7424566 (Open Web Text)

Max Activating Token Index: 380

Text #6

Max Range: 3.9631. Min Range: -3.9631

Max Act: 3.8275. Min Act: -0.1700

Data Index: 4407541 (Open Web Text)

Max Activating Token Index: 190

Text #7

Max Range: 3.9631. Min Range: -3.9631

Max Act: 3.7836. Min Act: -0.1700

Data Index: 7358499 (Open Web Text)

Max Activating Token Index: 1014

Text #8

Max Range: 3.9631. Min Range: -3.9631

Max Act: 3.7852. Min Act: -0.1700

Data Index: 8585226 (Open Web Text)

Max Activating Token Index: 836

Text #9

Max Range: 3.9631. Min Range: -3.9631

Max Act: 3.7891. Min Act: -0.1700

Data Index: 5393354 (Open Web Text)

Max Activating Token Index: 1019

Text #10

Max Range: 3.9631. Min Range: -3.9631

Max Act: 3.7578. Min Act: -0.1700

Data Index: 6450401 (Open Web Text)

Max Activating Token Index: 423

Text #11

Max Range: 3.9631. Min Range: -3.9631

Max Act: 3.7512. Min Act: -0.1700

Data Index: 2014526 (Open Web Text)

Max Activating Token Index: 760

Text #12

Max Range: 3.9631. Min Range: -3.9631

Max Act: 3.7430. Min Act: -0.1700

Data Index: 947718 (Open Web Text)

Max Activating Token Index: 538

Text #13

Max Range: 3.9631. Min Range: -3.9631

Max Act: 3.7399. Min Act: -0.1700

Data Index: 3462135 (Open Web Text)

Max Activating Token Index: 459

Text #14

Max Range: 3.9631. Min Range: -3.9631

Max Act: 3.7493. Min Act: -0.1700

Data Index: 6258139 (Open Web Text)

Max Activating Token Index: 227

Text #15

Max Range: 3.9631. Min Range: -3.9631

Max Act: 3.7381. Min Act: -0.1700

Data Index: 1370893 (Open Web Text)

Max Activating Token Index: 278

Text #16

Max Range: 3.9631. Min Range: -3.9631

Max Act: 3.7710. Min Act: -0.1700

Data Index: 8236076 (Open Web Text)

Max Activating Token Index: 217

Text #17

Max Range: 3.9631. Min Range: -3.9631

Max Act: 3.7472. Min Act: -0.1700

Data Index: 8724046 (Open Web Text)

Max Activating Token Index: 243

Text #18

Max Range: 3.9631. Min Range: -3.9631

Max Act: 3.7704. Min Act: -0.1700

Data Index: 3426115 (Open Web Text)

Max Activating Token Index: 252

Text #19

Max Range: 3.9631. Min Range: -3.9631

Max Act: 3.7565. Min Act: -0.1700

Data Index: 4911189 (Open Web Text)

Max Activating Token Index: 508