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

Dataset: Open Web Text

Neuron 121 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: 3.9757. Min Range: -3.9757

Max Act: 3.9757. Min Act: -0.1700

Data Index: 3644470 (Open Web Text)

Max Activating Token Index: 705

Text #1

Max Range: 3.9757. Min Range: -3.9757

Max Act: 3.9299. Min Act: -0.1700

Data Index: 3644474 (Open Web Text)

Max Activating Token Index: 563

Text #2

Max Range: 3.9757. Min Range: -3.9757

Max Act: 3.9397. Min Act: -0.1700

Data Index: 3644473 (Open Web Text)

Max Activating Token Index: 773

Text #3

Max Range: 3.9757. Min Range: -3.9757

Max Act: 3.9182. Min Act: -0.1700

Data Index: 3644471 (Open Web Text)

Max Activating Token Index: 700

Text #4

Max Range: 3.9757. Min Range: -3.9757

Max Act: 3.9628. Min Act: -0.1700

Data Index: 3644472 (Open Web Text)

Max Activating Token Index: 714

Text #5

Max Range: 3.9757. Min Range: -3.9757

Max Act: 3.8789. Min Act: -0.1700

Data Index: 4972388 (Open Web Text)

Max Activating Token Index: 634

Text #6

Max Range: 3.9757. Min Range: -3.9757

Max Act: 3.7957. Min Act: -0.1700

Data Index: 3344344 (Open Web Text)

Max Activating Token Index: 762

Text #7

Max Range: 3.9757. Min Range: -3.9757

Max Act: 3.7901. Min Act: -0.1700

Data Index: 7983382 (Open Web Text)

Max Activating Token Index: 329

Text #8

Max Range: 3.9757. Min Range: -3.9757

Max Act: 3.7758. Min Act: -0.1700

Data Index: 2551217 (Open Web Text)

Max Activating Token Index: 361

Text #9

Max Range: 3.9757. Min Range: -3.9757

Max Act: 3.7923. Min Act: -0.1700

Data Index: 863693 (Open Web Text)

Max Activating Token Index: 863

Text #10

Max Range: 3.9757. Min Range: -3.9757

Max Act: 3.7469. Min Act: -0.1700

Data Index: 5436713 (Open Web Text)

Max Activating Token Index: 649

Text #11

Max Range: 3.9757. Min Range: -3.9757

Max Act: 3.6938. Min Act: -0.1700

Data Index: 1371915 (Open Web Text)

Max Activating Token Index: 929

Text #12

Max Range: 3.9757. Min Range: -3.9757

Max Act: 3.7556. Min Act: -0.1700

Data Index: 5314684 (Open Web Text)

Max Activating Token Index: 971

Text #13

Max Range: 3.9757. Min Range: -3.9757

Max Act: 3.7632. Min Act: -0.1700

Data Index: 2551200 (Open Web Text)

Max Activating Token Index: 580

Text #14

Max Range: 3.9757. Min Range: -3.9757

Max Act: 3.7242. Min Act: -0.1700

Data Index: 3644469 (Open Web Text)

Max Activating Token Index: 687

Text #15

Max Range: 3.9757. Min Range: -3.9757

Max Act: 3.6894. Min Act: -0.1700

Data Index: 8477819 (Open Web Text)

Max Activating Token Index: 932

Text #16

Max Range: 3.9757. Min Range: -3.9757

Max Act: 3.6848. Min Act: -0.1700

Data Index: 7385938 (Open Web Text)

Max Activating Token Index: 643

Text #17

Max Range: 3.9757. Min Range: -3.9757

Max Act: 3.6756. Min Act: -0.1700

Data Index: 328 (Open Web Text)

Max Activating Token Index: 439

Text #18

Max Range: 3.9757. Min Range: -3.9757

Max Act: 3.6262. Min Act: -0.1700

Data Index: 6232287 (Open Web Text)

Max Activating Token Index: 1001

Text #19

Max Range: 3.9757. Min Range: -3.9757

Max Act: 3.6238. Min Act: -0.1700

Data Index: 2551203 (Open Web Text)

Max Activating Token Index: 970