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

Dataset: Open Web Text

Neuron 519 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: 3.7523. Min Range: -3.7523

Max Act: 3.7523. Min Act: -0.1700

Data Index: 8725444 (Open Web Text)

Max Activating Token Index: 183

Text #1

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.7115. Min Act: -0.1700

Data Index: 3164405 (Open Web Text)

Max Activating Token Index: 118

Text #2

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.6856. Min Act: -0.1700

Data Index: 392608 (Open Web Text)

Max Activating Token Index: 311

Text #3

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.6748. Min Act: -0.1700

Data Index: 7751673 (Open Web Text)

Max Activating Token Index: 50

Text #4

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.6222. Min Act: -0.1700

Data Index: 2475461 (Open Web Text)

Max Activating Token Index: 385

Text #5

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.6096. Min Act: -0.1700

Data Index: 4412596 (Open Web Text)

Max Activating Token Index: 38

Text #6

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.5893. Min Act: -0.1700

Data Index: 4275726 (Open Web Text)

Max Activating Token Index: 226

Text #7

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.5844. Min Act: -0.1700

Data Index: 2652256 (Open Web Text)

Max Activating Token Index: 582

Text #8

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.5899. Min Act: -0.1700

Data Index: 6548007 (Open Web Text)

Max Activating Token Index: 432

Text #9

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.5783. Min Act: -0.1700

Data Index: 3062101 (Open Web Text)

Max Activating Token Index: 421

Text #10

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.5866. Min Act: -0.1700

Data Index: 3945210 (Open Web Text)

Max Activating Token Index: 478

Text #11

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.5803. Min Act: -0.1700

Data Index: 8718967 (Open Web Text)

Max Activating Token Index: 771

Text #12

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.5468. Min Act: -0.1700

Data Index: 3808621 (Open Web Text)

Max Activating Token Index: 903

Text #13

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.5846. Min Act: -0.1700

Data Index: 8480681 (Open Web Text)

Max Activating Token Index: 792

Text #14

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.5465. Min Act: -0.1700

Data Index: 7670483 (Open Web Text)

Max Activating Token Index: 83

Text #15

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.5504. Min Act: -0.1700

Data Index: 3714068 (Open Web Text)

Max Activating Token Index: 127

Text #16

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.5589. Min Act: -0.1700

Data Index: 5214528 (Open Web Text)

Max Activating Token Index: 266

Text #17

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.5433. Min Act: -0.1700

Data Index: 4852429 (Open Web Text)

Max Activating Token Index: 220

Text #18

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.5543. Min Act: -0.1700

Data Index: 2939452 (Open Web Text)

Max Activating Token Index: 169

Text #19

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.5404. Min Act: -0.1700

Data Index: 3024369 (Open Web Text)

Max Activating Token Index: 539