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

Dataset: Open Web Text

Neuron 458 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: 3.2691. Min Range: -3.2691

Max Act: 3.2691. Min Act: -0.1700

Data Index: 5112583 (Open Web Text)

Max Activating Token Index: 14

Text #1

Max Range: 3.2691. Min Range: -3.2691

Max Act: 3.2324. Min Act: -0.1700

Data Index: 8123217 (Open Web Text)

Max Activating Token Index: 13

Text #2

Max Range: 3.2691. Min Range: -3.2691

Max Act: 3.2605. Min Act: -0.1700

Data Index: 1068884 (Open Web Text)

Max Activating Token Index: 105

Text #3

Max Range: 3.2691. Min Range: -3.2691

Max Act: 3.2442. Min Act: -0.1700

Data Index: 5085536 (Open Web Text)

Max Activating Token Index: 779

Text #4

Max Range: 3.2691. Min Range: -3.2691

Max Act: 3.2523. Min Act: -0.1700

Data Index: 8442713 (Open Web Text)

Max Activating Token Index: 469

Text #5

Max Range: 3.2691. Min Range: -3.2691

Max Act: 3.1974. Min Act: -0.1700

Data Index: 4610940 (Open Web Text)

Max Activating Token Index: 717

Text #6

Max Range: 3.2691. Min Range: -3.2691

Max Act: 3.2008. Min Act: -0.1700

Data Index: 8543703 (Open Web Text)

Max Activating Token Index: 321

Text #7

Max Range: 3.2691. Min Range: -3.2691

Max Act: 3.1493. Min Act: -0.1700

Data Index: 5742001 (Open Web Text)

Max Activating Token Index: 911

Text #8

Max Range: 3.2691. Min Range: -3.2691

Max Act: 3.1166. Min Act: -0.1700

Data Index: 7191137 (Open Web Text)

Max Activating Token Index: 42

Text #9

Max Range: 3.2691. Min Range: -3.2691

Max Act: 3.1244. Min Act: -0.1700

Data Index: 5141663 (Open Web Text)

Max Activating Token Index: 126

Text #10

Max Range: 3.2691. Min Range: -3.2691

Max Act: 3.0917. Min Act: -0.1700

Data Index: 7899481 (Open Web Text)

Max Activating Token Index: 237

Text #11

Max Range: 3.2691. Min Range: -3.2691

Max Act: 3.1080. Min Act: -0.1700

Data Index: 4281280 (Open Web Text)

Max Activating Token Index: 770

Text #12

Max Range: 3.2691. Min Range: -3.2691

Max Act: 3.1067. Min Act: -0.1700

Data Index: 2843870 (Open Web Text)

Max Activating Token Index: 291

Text #13

Max Range: 3.2691. Min Range: -3.2691

Max Act: 3.0552. Min Act: -0.1700

Data Index: 4493849 (Open Web Text)

Max Activating Token Index: 549

Text #14

Max Range: 3.2691. Min Range: -3.2691

Max Act: 3.0736. Min Act: -0.1700

Data Index: 4732666 (Open Web Text)

Max Activating Token Index: 420

Text #15

Max Range: 3.2691. Min Range: -3.2691

Max Act: 3.0840. Min Act: -0.1700

Data Index: 1451457 (Open Web Text)

Max Activating Token Index: 800

Text #16

Max Range: 3.2691. Min Range: -3.2691

Max Act: 3.0797. Min Act: -0.1700

Data Index: 7788711 (Open Web Text)

Max Activating Token Index: 405

Text #17

Max Range: 3.2691. Min Range: -3.2691

Max Act: 3.0732. Min Act: -0.1700

Data Index: 7519112 (Open Web Text)

Max Activating Token Index: 101

Text #18

Max Range: 3.2691. Min Range: -3.2691

Max Act: 3.0671. Min Act: -0.1700

Data Index: 5270433 (Open Web Text)

Max Activating Token Index: 234

Text #19

Max Range: 3.2691. Min Range: -3.2691

Max Act: 3.0375. Min Act: -0.1700

Data Index: 870699 (Open Web Text)

Max Activating Token Index: 332