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

Dataset: Open Web Text

Neuron 1737 in Layer 2

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: 5.2526. Min Range: -5.2526

Max Act: 5.2526. Min Act: -0.1700

Data Index: 8600219 (Open Web Text)

Max Activating Token Index: 27

Text #1

Max Range: 5.2526. Min Range: -5.2526

Max Act: 4.8088. Min Act: -0.1700

Data Index: 6733781 (Open Web Text)

Max Activating Token Index: 434

Text #2

Max Range: 5.2526. Min Range: -5.2526

Max Act: 4.7782. Min Act: -0.1700

Data Index: 7381392 (Open Web Text)

Max Activating Token Index: 414

Text #3

Max Range: 5.2526. Min Range: -5.2526

Max Act: 4.6652. Min Act: -0.1700

Data Index: 6423317 (Open Web Text)

Max Activating Token Index: 821

Text #4

Max Range: 5.2526. Min Range: -5.2526

Max Act: 4.6889. Min Act: -0.1700

Data Index: 5080976 (Open Web Text)

Max Activating Token Index: 90

Text #5

Max Range: 5.2526. Min Range: -5.2526

Max Act: 4.6778. Min Act: -0.1700

Data Index: 3260801 (Open Web Text)

Max Activating Token Index: 980

Text #6

Max Range: 5.2526. Min Range: -5.2526

Max Act: 4.6668. Min Act: -0.1700

Data Index: 7406852 (Open Web Text)

Max Activating Token Index: 327

Text #7

Max Range: 5.2526. Min Range: -5.2526

Max Act: 4.6157. Min Act: -0.1700

Data Index: 5143429 (Open Web Text)

Max Activating Token Index: 1007

Text #8

Max Range: 5.2526. Min Range: -5.2526

Max Act: 4.6055. Min Act: -0.1700

Data Index: 741657 (Open Web Text)

Max Activating Token Index: 120

Text #9

Max Range: 5.2526. Min Range: -5.2526

Max Act: 4.6072. Min Act: -0.1700

Data Index: 1573413 (Open Web Text)

Max Activating Token Index: 325

Text #10

Max Range: 5.2526. Min Range: -5.2526

Max Act: 4.6032. Min Act: -0.1700

Data Index: 3085345 (Open Web Text)

Max Activating Token Index: 54

Text #11

Max Range: 5.2526. Min Range: -5.2526

Max Act: 4.6013. Min Act: -0.1700

Data Index: 4290255 (Open Web Text)

Max Activating Token Index: 513

Text #12

Max Range: 5.2526. Min Range: -5.2526

Max Act: 4.6345. Min Act: -0.1700

Data Index: 8260746 (Open Web Text)

Max Activating Token Index: 982

Text #13

Max Range: 5.2526. Min Range: -5.2526

Max Act: 4.5537. Min Act: -0.1700

Data Index: 6911250 (Open Web Text)

Max Activating Token Index: 150

Text #14

Max Range: 5.2526. Min Range: -5.2526

Max Act: 4.5556. Min Act: -0.1700

Data Index: 137959 (Open Web Text)

Max Activating Token Index: 22

Text #15

Max Range: 5.2526. Min Range: -5.2526

Max Act: 4.5654. Min Act: -0.1700

Data Index: 6808580 (Open Web Text)

Max Activating Token Index: 328

Text #16

Max Range: 5.2526. Min Range: -5.2526

Max Act: 4.5681. Min Act: -0.1700

Data Index: 5915184 (Open Web Text)

Max Activating Token Index: 264

Text #17

Max Range: 5.2526. Min Range: -5.2526

Max Act: 4.5820. Min Act: -0.1700

Data Index: 2925135 (Open Web Text)

Max Activating Token Index: 911

Text #18

Max Range: 5.2526. Min Range: -5.2526

Max Act: 4.5547. Min Act: -0.1700

Data Index: 7476420 (Open Web Text)

Max Activating Token Index: 485

Text #19

Max Range: 5.2526. Min Range: -5.2526

Max Act: 4.5646. Min Act: -0.1700

Data Index: 7611487 (Open Web Text)

Max Activating Token Index: 493