Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer

Dataset: Open Web Text

Neuron 2025 in Layer 34

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')

Text #0

Max Range: 5.6379. Min Range: -5.6379

Max Act: 5.6379. Min Act: -0.1700

Data Index: 1080048 (Open Web Text)

Max Activating Token Index: 517

Text #1

Max Range: 5.6379. Min Range: -5.6379

Max Act: 5.4817. Min Act: -0.1700

Data Index: 1785230 (Open Web Text)

Max Activating Token Index: 650

Text #2

Max Range: 5.6379. Min Range: -5.6379

Max Act: 5.4504. Min Act: -0.1700

Data Index: 5116235 (Open Web Text)

Max Activating Token Index: 452

Text #3

Max Range: 5.6379. Min Range: -5.6379

Max Act: 5.3879. Min Act: -0.1700

Data Index: 7202225 (Open Web Text)

Max Activating Token Index: 848

Text #4

Max Range: 5.6379. Min Range: -5.6379

Max Act: 5.3879. Min Act: -0.1700

Data Index: 6897992 (Open Web Text)

Max Activating Token Index: 620

Text #5

Max Range: 5.6379. Min Range: -5.6379

Max Act: 5.3567. Min Act: -0.1699

Data Index: 2677017 (Open Web Text)

Max Activating Token Index: 1020

Text #6

Max Range: 5.6379. Min Range: -5.6379

Max Act: 5.3254. Min Act: -0.1700

Data Index: 2677019 (Open Web Text)

Max Activating Token Index: 930

Text #7

Max Range: 5.6379. Min Range: -5.6379

Max Act: 5.3254. Min Act: -0.1700

Data Index: 7844254 (Open Web Text)

Max Activating Token Index: 562

Text #8

Max Range: 5.6379. Min Range: -5.6379

Max Act: 5.3254. Min Act: -0.1700

Data Index: 986947 (Open Web Text)

Max Activating Token Index: 581

Text #9

Max Range: 5.6379. Min Range: -5.6379

Max Act: 5.2942. Min Act: -0.1700

Data Index: 8381920 (Open Web Text)

Max Activating Token Index: 550

Text #10

Max Range: 5.6379. Min Range: -5.6379

Max Act: 5.2629. Min Act: -0.1700

Data Index: 1254636 (Open Web Text)

Max Activating Token Index: 143

Text #11

Max Range: 5.6379. Min Range: -5.6379

Max Act: 5.2629. Min Act: -0.1700

Data Index: 4963317 (Open Web Text)

Max Activating Token Index: 218

Text #12

Max Range: 5.6379. Min Range: -5.6379

Max Act: 5.2629. Min Act: -0.1700

Data Index: 3242858 (Open Web Text)

Max Activating Token Index: 274

Text #13

Max Range: 5.6379. Min Range: -5.6379

Max Act: 5.2317. Min Act: -0.1700

Data Index: 3409952 (Open Web Text)

Max Activating Token Index: 1017

Text #14

Max Range: 5.6379. Min Range: -5.6379

Max Act: 5.2317. Min Act: -0.1700

Data Index: 804232 (Open Web Text)

Max Activating Token Index: 606

Text #15

Max Range: 5.6379. Min Range: -5.6379

Max Act: 5.2317. Min Act: -0.1700

Data Index: 264988 (Open Web Text)

Max Activating Token Index: 841

Text #16

Max Range: 5.6379. Min Range: -5.6379

Max Act: 5.2317. Min Act: -0.1700

Data Index: 1152533 (Open Web Text)

Max Activating Token Index: 229

Text #17

Max Range: 5.6379. Min Range: -5.6379

Max Act: 5.2004. Min Act: -0.1700

Data Index: 2707801 (Open Web Text)

Max Activating Token Index: 314

Text #18

Max Range: 5.6379. Min Range: -5.6379

Max Act: 5.1692. Min Act: -0.1700

Data Index: 7944775 (Open Web Text)

Max Activating Token Index: 443

Text #19

Max Range: 5.6379. Min Range: -5.6379

Max Act: 5.1692. Min Act: -0.1700

Data Index: 5117631 (Open Web Text)

Max Activating Token Index: 751