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

Dataset: Open Web Text

Neuron 1461 in Layer 3

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: 2.9640. Min Range: -2.9640

Max Act: 2.9457. Min Act: -0.1700

Data Index: 2408716 (Open Web Text)

Max Activating Token Index: 525

Text #1

Max Range: 2.9640. Min Range: -2.9640

Max Act: 2.9640. Min Act: -0.1700

Data Index: 4227830 (Open Web Text)

Max Activating Token Index: 460

Text #2

Max Range: 2.9640. Min Range: -2.9640

Max Act: 2.9058. Min Act: -0.1700

Data Index: 3818229 (Open Web Text)

Max Activating Token Index: 635

Text #3

Max Range: 2.9640. Min Range: -2.9640

Max Act: 2.9119. Min Act: -0.1700

Data Index: 376761 (Open Web Text)

Max Activating Token Index: 126

Text #4

Max Range: 2.9640. Min Range: -2.9640

Max Act: 2.9090. Min Act: -0.1700

Data Index: 2549543 (Open Web Text)

Max Activating Token Index: 891

Text #5

Max Range: 2.9640. Min Range: -2.9640

Max Act: 2.8883. Min Act: -0.1700

Data Index: 343542 (Open Web Text)

Max Activating Token Index: 782

Text #6

Max Range: 2.9640. Min Range: -2.9640

Max Act: 2.8726. Min Act: -0.1700

Data Index: 1553856 (Open Web Text)

Max Activating Token Index: 722

Text #7

Max Range: 2.9640. Min Range: -2.9640

Max Act: 2.8539. Min Act: -0.1700

Data Index: 8322909 (Open Web Text)

Max Activating Token Index: 667

Text #8

Max Range: 2.9640. Min Range: -2.9640

Max Act: 2.8387. Min Act: -0.1700

Data Index: 1936917 (Open Web Text)

Max Activating Token Index: 913

Text #9

Max Range: 2.9640. Min Range: -2.9640

Max Act: 2.8416. Min Act: -0.1700

Data Index: 3391609 (Open Web Text)

Max Activating Token Index: 660

Text #10

Max Range: 2.9640. Min Range: -2.9640

Max Act: 2.8347. Min Act: -0.1700

Data Index: 4720402 (Open Web Text)

Max Activating Token Index: 778

Text #11

Max Range: 2.9640. Min Range: -2.9640

Max Act: 2.8267. Min Act: -0.1700

Data Index: 1153028 (Open Web Text)

Max Activating Token Index: 667

Text #12

Max Range: 2.9640. Min Range: -2.9640

Max Act: 2.8255. Min Act: -0.1700

Data Index: 3805568 (Open Web Text)

Max Activating Token Index: 100

Text #13

Max Range: 2.9640. Min Range: -2.9640

Max Act: 2.7989. Min Act: -0.1700

Data Index: 883079 (Open Web Text)

Max Activating Token Index: 778

Text #14

Max Range: 2.9640. Min Range: -2.9640

Max Act: 2.8092. Min Act: -0.1700

Data Index: 3732346 (Open Web Text)

Max Activating Token Index: 336

Text #15

Max Range: 2.9640. Min Range: -2.9640

Max Act: 2.7872. Min Act: -0.1700

Data Index: 5802590 (Open Web Text)

Max Activating Token Index: 491

Text #16

Max Range: 2.9640. Min Range: -2.9640

Max Act: 2.7890. Min Act: -0.1700

Data Index: 2342533 (Open Web Text)

Max Activating Token Index: 589

Text #17

Max Range: 2.9640. Min Range: -2.9640

Max Act: 2.8002. Min Act: -0.1700

Data Index: 4825802 (Open Web Text)

Max Activating Token Index: 939

Text #18

Max Range: 2.9640. Min Range: -2.9640

Max Act: 2.7950. Min Act: -0.1700

Data Index: 3870845 (Open Web Text)

Max Activating Token Index: 851

Text #19

Max Range: 2.9640. Min Range: -2.9640

Max Act: 2.7864. Min Act: -0.1700

Data Index: 372681 (Open Web Text)

Max Activating Token Index: 699