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

Dataset: Open Web Text

Neuron 2567 in Layer 6

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: 4.4047. Min Range: -4.4047

Max Act: 4.4047. Min Act: -0.1700

Data Index: 7389625 (Open Web Text)

Max Activating Token Index: 402

Text #1

Max Range: 4.4047. Min Range: -4.4047

Max Act: 4.2342. Min Act: -0.1700

Data Index: 3946375 (Open Web Text)

Max Activating Token Index: 139

Text #2

Max Range: 4.4047. Min Range: -4.4047

Max Act: 4.1689. Min Act: -0.1700

Data Index: 2634518 (Open Web Text)

Max Activating Token Index: 759

Text #3

Max Range: 4.4047. Min Range: -4.4047

Max Act: 4.1960. Min Act: -0.1700

Data Index: 5150252 (Open Web Text)

Max Activating Token Index: 222

Text #4

Max Range: 4.4047. Min Range: -4.4047

Max Act: 4.1354. Min Act: -0.1700

Data Index: 8410830 (Open Web Text)

Max Activating Token Index: 293

Text #5

Max Range: 4.4047. Min Range: -4.4047

Max Act: 4.1550. Min Act: -0.1700

Data Index: 8573116 (Open Web Text)

Max Activating Token Index: 617

Text #6

Max Range: 4.4047. Min Range: -4.4047

Max Act: 4.1616. Min Act: -0.1700

Data Index: 8072853 (Open Web Text)

Max Activating Token Index: 850

Text #7

Max Range: 4.4047. Min Range: -4.4047

Max Act: 4.1602. Min Act: -0.1700

Data Index: 6018130 (Open Web Text)

Max Activating Token Index: 51

Text #8

Max Range: 4.4047. Min Range: -4.4047

Max Act: 4.1634. Min Act: -0.1700

Data Index: 7132562 (Open Web Text)

Max Activating Token Index: 741

Text #9

Max Range: 4.4047. Min Range: -4.4047

Max Act: 4.1196. Min Act: -0.1700

Data Index: 4121308 (Open Web Text)

Max Activating Token Index: 818

Text #10

Max Range: 4.4047. Min Range: -4.4047

Max Act: 4.0863. Min Act: -0.1700

Data Index: 7979474 (Open Web Text)

Max Activating Token Index: 691

Text #11

Max Range: 4.4047. Min Range: -4.4047

Max Act: 4.0944. Min Act: -0.1700

Data Index: 6227464 (Open Web Text)

Max Activating Token Index: 699

Text #12

Max Range: 4.4047. Min Range: -4.4047

Max Act: 4.0966. Min Act: -0.1700

Data Index: 7335 (Open Web Text)

Max Activating Token Index: 439

Text #13

Max Range: 4.4047. Min Range: -4.4047

Max Act: 4.1032. Min Act: -0.1700

Data Index: 6134369 (Open Web Text)

Max Activating Token Index: 716

Text #14

Max Range: 4.4047. Min Range: -4.4047

Max Act: 4.0994. Min Act: -0.1700

Data Index: 4161860 (Open Web Text)

Max Activating Token Index: 915

Text #15

Max Range: 4.4047. Min Range: -4.4047

Max Act: 4.1148. Min Act: -0.1700

Data Index: 4666915 (Open Web Text)

Max Activating Token Index: 564

Text #16

Max Range: 4.4047. Min Range: -4.4047

Max Act: 4.0408. Min Act: -0.1700

Data Index: 3157942 (Open Web Text)

Max Activating Token Index: 843

Text #17

Max Range: 4.4047. Min Range: -4.4047

Max Act: 4.0646. Min Act: -0.1700

Data Index: 3870162 (Open Web Text)

Max Activating Token Index: 235

Text #18

Max Range: 4.4047. Min Range: -4.4047

Max Act: 4.0450. Min Act: -0.1700

Data Index: 8702089 (Open Web Text)

Max Activating Token Index: 422

Text #19

Max Range: 4.4047. Min Range: -4.4047

Max Act: 4.0387. Min Act: -0.1700

Data Index: 6188637 (Open Web Text)

Max Activating Token Index: 728