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

Dataset: Open Web Text

Neuron 126 in Layer 2

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: 3.7615. Min Range: -3.7615

Max Act: 3.7615. Min Act: -0.1700

Data Index: 6863849 (Open Web Text)

Max Activating Token Index: 494

Text #1

Max Range: 3.7615. Min Range: -3.7615

Max Act: 3.6658. Min Act: -0.1700

Data Index: 8005325 (Open Web Text)

Max Activating Token Index: 389

Text #2

Max Range: 3.7615. Min Range: -3.7615

Max Act: 3.6793. Min Act: -0.1700

Data Index: 2481917 (Open Web Text)

Max Activating Token Index: 157

Text #3

Max Range: 3.7615. Min Range: -3.7615

Max Act: 3.6602. Min Act: -0.1700

Data Index: 5648476 (Open Web Text)

Max Activating Token Index: 479

Text #4

Max Range: 3.7615. Min Range: -3.7615

Max Act: 3.6324. Min Act: -0.1700

Data Index: 8391052 (Open Web Text)

Max Activating Token Index: 713

Text #5

Max Range: 3.7615. Min Range: -3.7615

Max Act: 3.6253. Min Act: -0.1700

Data Index: 4625444 (Open Web Text)

Max Activating Token Index: 410

Text #6

Max Range: 3.7615. Min Range: -3.7615

Max Act: 3.6018. Min Act: -0.1700

Data Index: 4427563 (Open Web Text)

Max Activating Token Index: 45

Text #7

Max Range: 3.7615. Min Range: -3.7615

Max Act: 3.6189. Min Act: -0.1700

Data Index: 4426718 (Open Web Text)

Max Activating Token Index: 579

Text #8

Max Range: 3.7615. Min Range: -3.7615

Max Act: 3.6052. Min Act: -0.1700

Data Index: 3506423 (Open Web Text)

Max Activating Token Index: 96

Text #9

Max Range: 3.7615. Min Range: -3.7615

Max Act: 3.6070. Min Act: -0.1700

Data Index: 8179158 (Open Web Text)

Max Activating Token Index: 835

Text #10

Max Range: 3.7615. Min Range: -3.7615

Max Act: 3.6157. Min Act: -0.1700

Data Index: 8136258 (Open Web Text)

Max Activating Token Index: 150

Text #11

Max Range: 3.7615. Min Range: -3.7615

Max Act: 3.5979. Min Act: -0.1700

Data Index: 2344382 (Open Web Text)

Max Activating Token Index: 376

Text #12

Max Range: 3.7615. Min Range: -3.7615

Max Act: 3.6241. Min Act: -0.1700

Data Index: 6588808 (Open Web Text)

Max Activating Token Index: 489

Text #13

Max Range: 3.7615. Min Range: -3.7615

Max Act: 3.6229. Min Act: -0.1700

Data Index: 5938759 (Open Web Text)

Max Activating Token Index: 14

Text #14

Max Range: 3.7615. Min Range: -3.7615

Max Act: 3.5781. Min Act: -0.1700

Data Index: 2914187 (Open Web Text)

Max Activating Token Index: 271

Text #15

Max Range: 3.7615. Min Range: -3.7615

Max Act: 3.5761. Min Act: -0.1700

Data Index: 3095992 (Open Web Text)

Max Activating Token Index: 598

Text #16

Max Range: 3.7615. Min Range: -3.7615

Max Act: 3.5843. Min Act: -0.1700

Data Index: 4496529 (Open Web Text)

Max Activating Token Index: 680

Text #17

Max Range: 3.7615. Min Range: -3.7615

Max Act: 3.5572. Min Act: -0.1700

Data Index: 3108456 (Open Web Text)

Max Activating Token Index: 232

Text #18

Max Range: 3.7615. Min Range: -3.7615

Max Act: 3.5753. Min Act: -0.1700

Data Index: 4737757 (Open Web Text)

Max Activating Token Index: 336

Text #19

Max Range: 3.7615. Min Range: -3.7615

Max Act: 3.5659. Min Act: -0.1700

Data Index: 5013249 (Open Web Text)

Max Activating Token Index: 944