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

Dataset: Open Web Text

Neuron 1902 in Layer 4

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: 4.8897. Min Range: -4.8897

Max Act: 4.8897. Min Act: -0.1700

Data Index: 4087043 (Open Web Text)

Max Activating Token Index: 688

Text #1

Max Range: 4.8897. Min Range: -4.8897

Max Act: 4.8611. Min Act: -0.1700

Data Index: 4661725 (Open Web Text)

Max Activating Token Index: 629

Text #2

Max Range: 4.8897. Min Range: -4.8897

Max Act: 4.8884. Min Act: -0.1700

Data Index: 1093164 (Open Web Text)

Max Activating Token Index: 512

Text #3

Max Range: 4.8897. Min Range: -4.8897

Max Act: 4.7956. Min Act: -0.1700

Data Index: 3665104 (Open Web Text)

Max Activating Token Index: 86

Text #4

Max Range: 4.8897. Min Range: -4.8897

Max Act: 4.7639. Min Act: -0.1700

Data Index: 5618863 (Open Web Text)

Max Activating Token Index: 189

Text #5

Max Range: 4.8897. Min Range: -4.8897

Max Act: 4.6695. Min Act: -0.1700

Data Index: 3824492 (Open Web Text)

Max Activating Token Index: 661

Text #6

Max Range: 4.8897. Min Range: -4.8897

Max Act: 4.6521. Min Act: -0.1700

Data Index: 2184443 (Open Web Text)

Max Activating Token Index: 915

Text #7

Max Range: 4.8897. Min Range: -4.8897

Max Act: 4.6612. Min Act: -0.1700

Data Index: 4460340 (Open Web Text)

Max Activating Token Index: 513

Text #8

Max Range: 4.8897. Min Range: -4.8897

Max Act: 4.6413. Min Act: -0.1700

Data Index: 5851522 (Open Web Text)

Max Activating Token Index: 905

Text #9

Max Range: 4.8897. Min Range: -4.8897

Max Act: 4.6627. Min Act: -0.1700

Data Index: 2571655 (Open Web Text)

Max Activating Token Index: 346

Text #10

Max Range: 4.8897. Min Range: -4.8897

Max Act: 4.6373. Min Act: -0.1700

Data Index: 7608225 (Open Web Text)

Max Activating Token Index: 578

Text #11

Max Range: 4.8897. Min Range: -4.8897

Max Act: 4.6474. Min Act: -0.1700

Data Index: 425226 (Open Web Text)

Max Activating Token Index: 60

Text #12

Max Range: 4.8897. Min Range: -4.8897

Max Act: 4.6319. Min Act: -0.1700

Data Index: 7026924 (Open Web Text)

Max Activating Token Index: 377

Text #13

Max Range: 4.8897. Min Range: -4.8897

Max Act: 4.6009. Min Act: -0.1700

Data Index: 2164016 (Open Web Text)

Max Activating Token Index: 413

Text #14

Max Range: 4.8897. Min Range: -4.8897

Max Act: 4.5880. Min Act: -0.1700

Data Index: 3352352 (Open Web Text)

Max Activating Token Index: 415

Text #15

Max Range: 4.8897. Min Range: -4.8897

Max Act: 4.6228. Min Act: -0.1700

Data Index: 7260817 (Open Web Text)

Max Activating Token Index: 860

Text #16

Max Range: 4.8897. Min Range: -4.8897

Max Act: 4.5920. Min Act: -0.1700

Data Index: 2486023 (Open Web Text)

Max Activating Token Index: 359

Text #17

Max Range: 4.8897. Min Range: -4.8897

Max Act: 4.5519. Min Act: -0.1700

Data Index: 3027159 (Open Web Text)

Max Activating Token Index: 524

Text #18

Max Range: 4.8897. Min Range: -4.8897

Max Act: 4.5322. Min Act: -0.1700

Data Index: 538878 (Open Web Text)

Max Activating Token Index: 553

Text #19

Max Range: 4.8897. Min Range: -4.8897

Max Act: 4.5501. Min Act: -0.1700

Data Index: 4484139 (Open Web Text)

Max Activating Token Index: 364