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

Dataset: Open Web Text

Neuron 2608 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: 4.2381. Min Range: -4.2381

Max Act: 4.2381. Min Act: -0.1700

Data Index: 2819503 (Open Web Text)

Max Activating Token Index: 719

Text #1

Max Range: 4.2381. Min Range: -4.2381

Max Act: 3.9832. Min Act: -0.1700

Data Index: 6161438 (Open Web Text)

Max Activating Token Index: 593

Text #2

Max Range: 4.2381. Min Range: -4.2381

Max Act: 3.9620. Min Act: -0.1700

Data Index: 985877 (Open Web Text)

Max Activating Token Index: 134

Text #3

Max Range: 4.2381. Min Range: -4.2381

Max Act: 3.9537. Min Act: -0.1700

Data Index: 8167267 (Open Web Text)

Max Activating Token Index: 271

Text #4

Max Range: 4.2381. Min Range: -4.2381

Max Act: 3.9089. Min Act: -0.1700

Data Index: 6327983 (Open Web Text)

Max Activating Token Index: 1008

Text #5

Max Range: 4.2381. Min Range: -4.2381

Max Act: 3.8504. Min Act: -0.1700

Data Index: 5134354 (Open Web Text)

Max Activating Token Index: 988

Text #6

Max Range: 4.2381. Min Range: -4.2381

Max Act: 3.8265. Min Act: -0.1700

Data Index: 5381921 (Open Web Text)

Max Activating Token Index: 265

Text #7

Max Range: 4.2381. Min Range: -4.2381

Max Act: 3.7920. Min Act: -0.1700

Data Index: 1996802 (Open Web Text)

Max Activating Token Index: 1018

Text #8

Max Range: 4.2381. Min Range: -4.2381

Max Act: 3.7691. Min Act: -0.1700

Data Index: 5134351 (Open Web Text)

Max Activating Token Index: 304

Text #9

Max Range: 4.2381. Min Range: -4.2381

Max Act: 3.7675. Min Act: -0.1700

Data Index: 5115943 (Open Web Text)

Max Activating Token Index: 89

Text #10

Max Range: 4.2381. Min Range: -4.2381

Max Act: 3.7312. Min Act: -0.1700

Data Index: 6246607 (Open Web Text)

Max Activating Token Index: 670

Text #11

Max Range: 4.2381. Min Range: -4.2381

Max Act: 3.7469. Min Act: -0.1700

Data Index: 3874665 (Open Web Text)

Max Activating Token Index: 845

Text #12

Max Range: 4.2381. Min Range: -4.2381

Max Act: 3.7131. Min Act: -0.1700

Data Index: 2963307 (Open Web Text)

Max Activating Token Index: 311

Text #13

Max Range: 4.2381. Min Range: -4.2381

Max Act: 3.7431. Min Act: -0.1700

Data Index: 1187993 (Open Web Text)

Max Activating Token Index: 674

Text #14

Max Range: 4.2381. Min Range: -4.2381

Max Act: 3.7340. Min Act: -0.1700

Data Index: 1410395 (Open Web Text)

Max Activating Token Index: 710

Text #15

Max Range: 4.2381. Min Range: -4.2381

Max Act: 3.7083. Min Act: -0.1700

Data Index: 8765586 (Open Web Text)

Max Activating Token Index: 873

Text #16

Max Range: 4.2381. Min Range: -4.2381

Max Act: 3.6684. Min Act: -0.1700

Data Index: 3419625 (Open Web Text)

Max Activating Token Index: 1007

Text #17

Max Range: 4.2381. Min Range: -4.2381

Max Act: 3.6851. Min Act: -0.1700

Data Index: 8704488 (Open Web Text)

Max Activating Token Index: 918

Text #18

Max Range: 4.2381. Min Range: -4.2381

Max Act: 3.6930. Min Act: -0.1700

Data Index: 1919486 (Open Web Text)

Max Activating Token Index: 113

Text #19

Max Range: 4.2381. Min Range: -4.2381

Max Act: 3.6616. Min Act: -0.1700

Data Index: 3041551 (Open Web Text)

Max Activating Token Index: 871