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

Dataset: Open Web Text

Neuron 2092 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: 4.6909. Min Range: -4.6909

Max Act: 4.6909. Min Act: -0.1700

Data Index: 5293137 (Open Web Text)

Max Activating Token Index: 489

Text #1

Max Range: 4.6909. Min Range: -4.6909

Max Act: 4.4986. Min Act: -0.1700

Data Index: 1845336 (Open Web Text)

Max Activating Token Index: 31

Text #2

Max Range: 4.6909. Min Range: -4.6909

Max Act: 4.5267. Min Act: -0.1700

Data Index: 1967571 (Open Web Text)

Max Activating Token Index: 749

Text #3

Max Range: 4.6909. Min Range: -4.6909

Max Act: 4.5047. Min Act: -0.1700

Data Index: 7151991 (Open Web Text)

Max Activating Token Index: 610

Text #4

Max Range: 4.6909. Min Range: -4.6909

Max Act: 4.5234. Min Act: -0.1700

Data Index: 1583408 (Open Web Text)

Max Activating Token Index: 350

Text #5

Max Range: 4.6909. Min Range: -4.6909

Max Act: 4.5084. Min Act: -0.1700

Data Index: 4927058 (Open Web Text)

Max Activating Token Index: 562

Text #6

Max Range: 4.6909. Min Range: -4.6909

Max Act: 4.4788. Min Act: -0.1700

Data Index: 2032535 (Open Web Text)

Max Activating Token Index: 965

Text #7

Max Range: 4.6909. Min Range: -4.6909

Max Act: 4.4460. Min Act: -0.1700

Data Index: 8431547 (Open Web Text)

Max Activating Token Index: 752

Text #8

Max Range: 4.6909. Min Range: -4.6909

Max Act: 4.4291. Min Act: -0.1700

Data Index: 2546692 (Open Web Text)

Max Activating Token Index: 949

Text #9

Max Range: 4.6909. Min Range: -4.6909

Max Act: 4.4262. Min Act: -0.1700

Data Index: 5949786 (Open Web Text)

Max Activating Token Index: 419

Text #10

Max Range: 4.6909. Min Range: -4.6909

Max Act: 4.4479. Min Act: -0.1700

Data Index: 6597761 (Open Web Text)

Max Activating Token Index: 682

Text #11

Max Range: 4.6909. Min Range: -4.6909

Max Act: 4.3911. Min Act: -0.1700

Data Index: 1449684 (Open Web Text)

Max Activating Token Index: 497

Text #12

Max Range: 4.6909. Min Range: -4.6909

Max Act: 4.3960. Min Act: -0.1700

Data Index: 2179575 (Open Web Text)

Max Activating Token Index: 783

Text #13

Max Range: 4.6909. Min Range: -4.6909

Max Act: 4.4185. Min Act: -0.1700

Data Index: 7640931 (Open Web Text)

Max Activating Token Index: 413

Text #14

Max Range: 4.6909. Min Range: -4.6909

Max Act: 4.4071. Min Act: -0.1700

Data Index: 6696130 (Open Web Text)

Max Activating Token Index: 372

Text #15

Max Range: 4.6909. Min Range: -4.6909

Max Act: 4.3748. Min Act: -0.1700

Data Index: 3540926 (Open Web Text)

Max Activating Token Index: 691

Text #16

Max Range: 4.6909. Min Range: -4.6909

Max Act: 4.3553. Min Act: -0.1700

Data Index: 4592606 (Open Web Text)

Max Activating Token Index: 909

Text #17

Max Range: 4.6909. Min Range: -4.6909

Max Act: 4.3589. Min Act: -0.1700

Data Index: 4451967 (Open Web Text)

Max Activating Token Index: 514

Text #18

Max Range: 4.6909. Min Range: -4.6909

Max Act: 4.3455. Min Act: -0.1700

Data Index: 1255981 (Open Web Text)

Max Activating Token Index: 188

Text #19

Max Range: 4.6909. Min Range: -4.6909

Max Act: 4.3628. Min Act: -0.1700

Data Index: 3864966 (Open Web Text)

Max Activating Token Index: 465