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

Dataset: Open Web Text

Neuron 2528 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: 3.8334. Min Range: -3.8334

Max Act: 3.8334. Min Act: -0.1700

Data Index: 7667628 (Open Web Text)

Max Activating Token Index: 184

Text #1

Max Range: 3.8334. Min Range: -3.8334

Max Act: 3.8049. Min Act: -0.1700

Data Index: 946890 (Open Web Text)

Max Activating Token Index: 102

Text #2

Max Range: 3.8334. Min Range: -3.8334

Max Act: 3.7537. Min Act: -0.1700

Data Index: 351660 (Open Web Text)

Max Activating Token Index: 128

Text #3

Max Range: 3.8334. Min Range: -3.8334

Max Act: 3.7621. Min Act: -0.1700

Data Index: 1479410 (Open Web Text)

Max Activating Token Index: 154

Text #4

Max Range: 3.8334. Min Range: -3.8334

Max Act: 3.7520. Min Act: -0.1700

Data Index: 655502 (Open Web Text)

Max Activating Token Index: 361

Text #5

Max Range: 3.8334. Min Range: -3.8334

Max Act: 3.7381. Min Act: -0.1700

Data Index: 3104739 (Open Web Text)

Max Activating Token Index: 389

Text #6

Max Range: 3.8334. Min Range: -3.8334

Max Act: 3.7527. Min Act: -0.1700

Data Index: 1272566 (Open Web Text)

Max Activating Token Index: 278

Text #7

Max Range: 3.8334. Min Range: -3.8334

Max Act: 3.7259. Min Act: -0.1700

Data Index: 4772362 (Open Web Text)

Max Activating Token Index: 287

Text #8

Max Range: 3.8334. Min Range: -3.8334

Max Act: 3.6880. Min Act: -0.1700

Data Index: 2490255 (Open Web Text)

Max Activating Token Index: 51

Text #9

Max Range: 3.8334. Min Range: -3.8334

Max Act: 3.7171. Min Act: -0.1700

Data Index: 400608 (Open Web Text)

Max Activating Token Index: 130

Text #10

Max Range: 3.8334. Min Range: -3.8334

Max Act: 3.7007. Min Act: -0.1700

Data Index: 4213041 (Open Web Text)

Max Activating Token Index: 88

Text #11

Max Range: 3.8334. Min Range: -3.8334

Max Act: 3.7033. Min Act: -0.1700

Data Index: 600186 (Open Web Text)

Max Activating Token Index: 32

Text #12

Max Range: 3.8334. Min Range: -3.8334

Max Act: 3.6813. Min Act: -0.1700

Data Index: 5314036 (Open Web Text)

Max Activating Token Index: 163

Text #13

Max Range: 3.8334. Min Range: -3.8334

Max Act: 3.6873. Min Act: -0.1700

Data Index: 3340674 (Open Web Text)

Max Activating Token Index: 115

Text #14

Max Range: 3.8334. Min Range: -3.8334

Max Act: 3.6890. Min Act: -0.1700

Data Index: 2260624 (Open Web Text)

Max Activating Token Index: 132

Text #15

Max Range: 3.8334. Min Range: -3.8334

Max Act: 3.6790. Min Act: -0.1700

Data Index: 6175557 (Open Web Text)

Max Activating Token Index: 58

Text #16

Max Range: 3.8334. Min Range: -3.8334

Max Act: 3.6818. Min Act: -0.1700

Data Index: 1906 (Open Web Text)

Max Activating Token Index: 120

Text #17

Max Range: 3.8334. Min Range: -3.8334

Max Act: 3.6769. Min Act: -0.1700

Data Index: 2967191 (Open Web Text)

Max Activating Token Index: 102

Text #18

Max Range: 3.8334. Min Range: -3.8334

Max Act: 3.6748. Min Act: -0.1700

Data Index: 3447723 (Open Web Text)

Max Activating Token Index: 114

Text #19

Max Range: 3.8334. Min Range: -3.8334

Max Act: 3.6759. Min Act: -0.1700

Data Index: 4453205 (Open Web Text)

Max Activating Token Index: 193