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

Dataset: Open Web Text

Neuron 2793 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: 4.8317. Min Range: -4.8317

Max Act: 4.8317. Min Act: -0.1700

Data Index: 5431929 (Open Web Text)

Max Activating Token Index: 569

Text #1

Max Range: 4.8317. Min Range: -4.8317

Max Act: 4.7612. Min Act: -0.1700

Data Index: 5822745 (Open Web Text)

Max Activating Token Index: 868

Text #2

Max Range: 4.8317. Min Range: -4.8317

Max Act: 4.7192. Min Act: -0.1700

Data Index: 116929 (Open Web Text)

Max Activating Token Index: 342

Text #3

Max Range: 4.8317. Min Range: -4.8317

Max Act: 4.7301. Min Act: -0.1700

Data Index: 4148062 (Open Web Text)

Max Activating Token Index: 293

Text #4

Max Range: 4.8317. Min Range: -4.8317

Max Act: 4.6823. Min Act: -0.1700

Data Index: 5684328 (Open Web Text)

Max Activating Token Index: 311

Text #5

Max Range: 4.8317. Min Range: -4.8317

Max Act: 4.6248. Min Act: -0.1700

Data Index: 3493119 (Open Web Text)

Max Activating Token Index: 879

Text #6

Max Range: 4.8317. Min Range: -4.8317

Max Act: 4.6284. Min Act: -0.1700

Data Index: 3504857 (Open Web Text)

Max Activating Token Index: 255

Text #7

Max Range: 4.8317. Min Range: -4.8317

Max Act: 4.6419. Min Act: -0.1700

Data Index: 1087137 (Open Web Text)

Max Activating Token Index: 414

Text #8

Max Range: 4.8317. Min Range: -4.8317

Max Act: 4.6621. Min Act: -0.1700

Data Index: 8099268 (Open Web Text)

Max Activating Token Index: 641

Text #9

Max Range: 4.8317. Min Range: -4.8317

Max Act: 4.6498. Min Act: -0.1700

Data Index: 6389900 (Open Web Text)

Max Activating Token Index: 365

Text #10

Max Range: 4.8317. Min Range: -4.8317

Max Act: 4.6306. Min Act: -0.1700

Data Index: 3480987 (Open Web Text)

Max Activating Token Index: 627

Text #11

Max Range: 4.8317. Min Range: -4.8317

Max Act: 4.6179. Min Act: -0.1700

Data Index: 4102651 (Open Web Text)

Max Activating Token Index: 829

Text #12

Max Range: 4.8317. Min Range: -4.8317

Max Act: 4.6021. Min Act: -0.1700

Data Index: 6065229 (Open Web Text)

Max Activating Token Index: 780

Text #13

Max Range: 4.8317. Min Range: -4.8317

Max Act: 4.6223. Min Act: -0.1700

Data Index: 4229104 (Open Web Text)

Max Activating Token Index: 107

Text #14

Max Range: 4.8317. Min Range: -4.8317

Max Act: 4.6027. Min Act: -0.1700

Data Index: 8290417 (Open Web Text)

Max Activating Token Index: 456

Text #15

Max Range: 4.8317. Min Range: -4.8317

Max Act: 4.5938. Min Act: -0.1700

Data Index: 3523630 (Open Web Text)

Max Activating Token Index: 541

Text #16

Max Range: 4.8317. Min Range: -4.8317

Max Act: 4.5990. Min Act: -0.1700

Data Index: 716824 (Open Web Text)

Max Activating Token Index: 139

Text #17

Max Range: 4.8317. Min Range: -4.8317

Max Act: 4.6142. Min Act: -0.1700

Data Index: 451406 (Open Web Text)

Max Activating Token Index: 467

Text #18

Max Range: 4.8317. Min Range: -4.8317

Max Act: 4.5891. Min Act: -0.1700

Data Index: 557474 (Open Web Text)

Max Activating Token Index: 377

Text #19

Max Range: 4.8317. Min Range: -4.8317

Max Act: 4.5778. Min Act: -0.1700

Data Index: 2774315 (Open Web Text)

Max Activating Token Index: 520