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

Dataset: Open Web Text

Neuron 1126 in Layer 1

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: 4.5415. Min Range: -4.5415

Max Act: 4.5415. Min Act: -0.1700

Data Index: 8253654 (Open Web Text)

Max Activating Token Index: 612

Text #1

Max Range: 4.5415. Min Range: -4.5415

Max Act: 4.4462. Min Act: -0.1700

Data Index: 4452233 (Open Web Text)

Max Activating Token Index: 83

Text #2

Max Range: 4.5415. Min Range: -4.5415

Max Act: 4.4550. Min Act: -0.1700

Data Index: 7222359 (Open Web Text)

Max Activating Token Index: 304

Text #3

Max Range: 4.5415. Min Range: -4.5415

Max Act: 4.4569. Min Act: -0.1700

Data Index: 5147357 (Open Web Text)

Max Activating Token Index: 518

Text #4

Max Range: 4.5415. Min Range: -4.5415

Max Act: 4.4391. Min Act: -0.1700

Data Index: 3753679 (Open Web Text)

Max Activating Token Index: 655

Text #5

Max Range: 4.5415. Min Range: -4.5415

Max Act: 4.4286. Min Act: -0.1700

Data Index: 1775743 (Open Web Text)

Max Activating Token Index: 694

Text #6

Max Range: 4.5415. Min Range: -4.5415

Max Act: 4.4251. Min Act: -0.1700

Data Index: 7565451 (Open Web Text)

Max Activating Token Index: 448

Text #7

Max Range: 4.5415. Min Range: -4.5415

Max Act: 4.4008. Min Act: -0.1700

Data Index: 1105493 (Open Web Text)

Max Activating Token Index: 367

Text #8

Max Range: 4.5415. Min Range: -4.5415

Max Act: 4.3936. Min Act: -0.1700

Data Index: 1360718 (Open Web Text)

Max Activating Token Index: 300

Text #9

Max Range: 4.5415. Min Range: -4.5415

Max Act: 4.3853. Min Act: -0.1700

Data Index: 5598352 (Open Web Text)

Max Activating Token Index: 370

Text #10

Max Range: 4.5415. Min Range: -4.5415

Max Act: 4.3863. Min Act: -0.1700

Data Index: 7246649 (Open Web Text)

Max Activating Token Index: 474

Text #11

Max Range: 4.5415. Min Range: -4.5415

Max Act: 4.3983. Min Act: -0.1700

Data Index: 371057 (Open Web Text)

Max Activating Token Index: 292

Text #12

Max Range: 4.5415. Min Range: -4.5415

Max Act: 4.3847. Min Act: -0.1700

Data Index: 4528209 (Open Web Text)

Max Activating Token Index: 653

Text #13

Max Range: 4.5415. Min Range: -4.5415

Max Act: 4.4063. Min Act: -0.1700

Data Index: 2548047 (Open Web Text)

Max Activating Token Index: 68

Text #14

Max Range: 4.5415. Min Range: -4.5415

Max Act: 4.3919. Min Act: -0.1700

Data Index: 8803305 (Open Web Text)

Max Activating Token Index: 309

Text #15

Max Range: 4.5415. Min Range: -4.5415

Max Act: 4.3835. Min Act: -0.1700

Data Index: 2224221 (Open Web Text)

Max Activating Token Index: 601

Text #16

Max Range: 4.5415. Min Range: -4.5415

Max Act: 4.3924. Min Act: -0.1700

Data Index: 6996921 (Open Web Text)

Max Activating Token Index: 372

Text #17

Max Range: 4.5415. Min Range: -4.5415

Max Act: 4.4088. Min Act: -0.1700

Data Index: 2312833 (Open Web Text)

Max Activating Token Index: 384

Text #18

Max Range: 4.5415. Min Range: -4.5415

Max Act: 4.3669. Min Act: -0.1700

Data Index: 7094585 (Open Web Text)

Max Activating Token Index: 809

Text #19

Max Range: 4.5415. Min Range: -4.5415

Max Act: 4.3680. Min Act: -0.1700

Data Index: 722724 (Open Web Text)

Max Activating Token Index: 602