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

Dataset: Open Web Text

Neuron 1364 in Layer 5

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: 4.6789. Min Range: -4.6789

Max Act: 4.6789. Min Act: -0.1700

Data Index: 7470256 (Open Web Text)

Max Activating Token Index: 602

Text #1

Max Range: 4.6789. Min Range: -4.6789

Max Act: 4.6415. Min Act: -0.1700

Data Index: 6781929 (Open Web Text)

Max Activating Token Index: 278

Text #2

Max Range: 4.6789. Min Range: -4.6789

Max Act: 4.5950. Min Act: -0.1700

Data Index: 8086260 (Open Web Text)

Max Activating Token Index: 586

Text #3

Max Range: 4.6789. Min Range: -4.6789

Max Act: 4.5819. Min Act: -0.1700

Data Index: 528327 (Open Web Text)

Max Activating Token Index: 124

Text #4

Max Range: 4.6789. Min Range: -4.6789

Max Act: 4.6014. Min Act: -0.1700

Data Index: 4853270 (Open Web Text)

Max Activating Token Index: 481

Text #5

Max Range: 4.6789. Min Range: -4.6789

Max Act: 4.5719. Min Act: -0.1700

Data Index: 7726158 (Open Web Text)

Max Activating Token Index: 507

Text #6

Max Range: 4.6789. Min Range: -4.6789

Max Act: 4.5552. Min Act: -0.1700

Data Index: 5790532 (Open Web Text)

Max Activating Token Index: 306

Text #7

Max Range: 4.6789. Min Range: -4.6789

Max Act: 4.5501. Min Act: -0.1700

Data Index: 1197431 (Open Web Text)

Max Activating Token Index: 321

Text #8

Max Range: 4.6789. Min Range: -4.6789

Max Act: 4.5453. Min Act: -0.1700

Data Index: 6365617 (Open Web Text)

Max Activating Token Index: 414

Text #9

Max Range: 4.6789. Min Range: -4.6789

Max Act: 4.5252. Min Act: -0.1700

Data Index: 4992036 (Open Web Text)

Max Activating Token Index: 194

Text #10

Max Range: 4.6789. Min Range: -4.6789

Max Act: 4.5312. Min Act: -0.1700

Data Index: 4971160 (Open Web Text)

Max Activating Token Index: 420

Text #11

Max Range: 4.6789. Min Range: -4.6789

Max Act: 4.5146. Min Act: -0.1700

Data Index: 6554795 (Open Web Text)

Max Activating Token Index: 388

Text #12

Max Range: 4.6789. Min Range: -4.6789

Max Act: 4.5525. Min Act: -0.1700

Data Index: 5228079 (Open Web Text)

Max Activating Token Index: 853

Text #13

Max Range: 4.6789. Min Range: -4.6789

Max Act: 4.5302. Min Act: -0.1700

Data Index: 6075088 (Open Web Text)

Max Activating Token Index: 275

Text #14

Max Range: 4.6789. Min Range: -4.6789

Max Act: 4.5221. Min Act: -0.1700

Data Index: 6137266 (Open Web Text)

Max Activating Token Index: 607

Text #15

Max Range: 4.6789. Min Range: -4.6789

Max Act: 4.4895. Min Act: -0.1700

Data Index: 6122891 (Open Web Text)

Max Activating Token Index: 788

Text #16

Max Range: 4.6789. Min Range: -4.6789

Max Act: 4.4853. Min Act: -0.1700

Data Index: 1405531 (Open Web Text)

Max Activating Token Index: 549

Text #17

Max Range: 4.6789. Min Range: -4.6789

Max Act: 4.4968. Min Act: -0.1700

Data Index: 3088533 (Open Web Text)

Max Activating Token Index: 348

Text #18

Max Range: 4.6789. Min Range: -4.6789

Max Act: 4.4810. Min Act: -0.1700

Data Index: 7891736 (Open Web Text)

Max Activating Token Index: 761

Text #19

Max Range: 4.6789. Min Range: -4.6789

Max Act: 4.4874. Min Act: -0.1700

Data Index: 5431221 (Open Web Text)

Max Activating Token Index: 966