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

Dataset: Open Web Text

Neuron 1680 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: 5.6267. Min Range: -5.6267

Max Act: 5.6267. Min Act: -0.1700

Data Index: 6003820 (Open Web Text)

Max Activating Token Index: 245

Text #1

Max Range: 5.6267. Min Range: -5.6267

Max Act: 5.5777. Min Act: -0.1700

Data Index: 3781733 (Open Web Text)

Max Activating Token Index: 261

Text #2

Max Range: 5.6267. Min Range: -5.6267

Max Act: 5.6031. Min Act: -0.1700

Data Index: 870199 (Open Web Text)

Max Activating Token Index: 450

Text #3

Max Range: 5.6267. Min Range: -5.6267

Max Act: 5.5586. Min Act: -0.1700

Data Index: 5076670 (Open Web Text)

Max Activating Token Index: 529

Text #4

Max Range: 5.6267. Min Range: -5.6267

Max Act: 5.5477. Min Act: -0.1700

Data Index: 500641 (Open Web Text)

Max Activating Token Index: 382

Text #5

Max Range: 5.6267. Min Range: -5.6267

Max Act: 5.4914. Min Act: -0.1700

Data Index: 3325817 (Open Web Text)

Max Activating Token Index: 481

Text #6

Max Range: 5.6267. Min Range: -5.6267

Max Act: 5.5286. Min Act: -0.1700

Data Index: 7660429 (Open Web Text)

Max Activating Token Index: 234

Text #7

Max Range: 5.6267. Min Range: -5.6267

Max Act: 5.5285. Min Act: -0.1700

Data Index: 4827826 (Open Web Text)

Max Activating Token Index: 764

Text #8

Max Range: 5.6267. Min Range: -5.6267

Max Act: 5.4768. Min Act: -0.1700

Data Index: 5768060 (Open Web Text)

Max Activating Token Index: 169

Text #9

Max Range: 5.6267. Min Range: -5.6267

Max Act: 5.4523. Min Act: -0.1700

Data Index: 948194 (Open Web Text)

Max Activating Token Index: 360

Text #10

Max Range: 5.6267. Min Range: -5.6267

Max Act: 5.4380. Min Act: -0.1700

Data Index: 395322 (Open Web Text)

Max Activating Token Index: 797

Text #11

Max Range: 5.6267. Min Range: -5.6267

Max Act: 5.4428. Min Act: -0.1700

Data Index: 4258274 (Open Web Text)

Max Activating Token Index: 950

Text #12

Max Range: 5.6267. Min Range: -5.6267

Max Act: 5.4561. Min Act: -0.1700

Data Index: 8678246 (Open Web Text)

Max Activating Token Index: 382

Text #13

Max Range: 5.6267. Min Range: -5.6267

Max Act: 5.4920. Min Act: -0.1700

Data Index: 6198528 (Open Web Text)

Max Activating Token Index: 388

Text #14

Max Range: 5.6267. Min Range: -5.6267

Max Act: 5.4662. Min Act: -0.1700

Data Index: 7881790 (Open Web Text)

Max Activating Token Index: 403

Text #15

Max Range: 5.6267. Min Range: -5.6267

Max Act: 5.4380. Min Act: -0.1700

Data Index: 7877287 (Open Web Text)

Max Activating Token Index: 354

Text #16

Max Range: 5.6267. Min Range: -5.6267

Max Act: 5.4123. Min Act: -0.1700

Data Index: 1891957 (Open Web Text)

Max Activating Token Index: 216

Text #17

Max Range: 5.6267. Min Range: -5.6267

Max Act: 5.3774. Min Act: -0.1700

Data Index: 4224816 (Open Web Text)

Max Activating Token Index: 103

Text #18

Max Range: 5.6267. Min Range: -5.6267

Max Act: 5.3856. Min Act: -0.1700

Data Index: 3427674 (Open Web Text)

Max Activating Token Index: 169

Text #19

Max Range: 5.6267. Min Range: -5.6267

Max Act: 5.3606. Min Act: -0.1700

Data Index: 2160446 (Open Web Text)

Max Activating Token Index: 617