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

Dataset: Open Web Text

Neuron 2331 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: 5.4610. Min Range: -5.4610

Max Act: 5.4610. Min Act: -0.1700

Data Index: 206388 (Open Web Text)

Max Activating Token Index: 344

Text #1

Max Range: 5.4610. Min Range: -5.4610

Max Act: 5.4032. Min Act: -0.1700

Data Index: 1705556 (Open Web Text)

Max Activating Token Index: 166

Text #2

Max Range: 5.4610. Min Range: -5.4610

Max Act: 5.3635. Min Act: -0.1700

Data Index: 8032538 (Open Web Text)

Max Activating Token Index: 1008

Text #3

Max Range: 5.4610. Min Range: -5.4610

Max Act: 5.2795. Min Act: -0.1700

Data Index: 841859 (Open Web Text)

Max Activating Token Index: 291

Text #4

Max Range: 5.4610. Min Range: -5.4610

Max Act: 5.2576. Min Act: -0.1700

Data Index: 4661657 (Open Web Text)

Max Activating Token Index: 839

Text #5

Max Range: 5.4610. Min Range: -5.4610

Max Act: 5.3019. Min Act: -0.1700

Data Index: 5390179 (Open Web Text)

Max Activating Token Index: 612

Text #6

Max Range: 5.4610. Min Range: -5.4610

Max Act: 5.2620. Min Act: -0.1700

Data Index: 1760043 (Open Web Text)

Max Activating Token Index: 525

Text #7

Max Range: 5.4610. Min Range: -5.4610

Max Act: 5.2216. Min Act: -0.1700

Data Index: 4216756 (Open Web Text)

Max Activating Token Index: 10

Text #8

Max Range: 5.4610. Min Range: -5.4610

Max Act: 5.2604. Min Act: -0.1700

Data Index: 4362525 (Open Web Text)

Max Activating Token Index: 814

Text #9

Max Range: 5.4610. Min Range: -5.4610

Max Act: 5.1751. Min Act: -0.1700

Data Index: 8359713 (Open Web Text)

Max Activating Token Index: 213

Text #10

Max Range: 5.4610. Min Range: -5.4610

Max Act: 5.1622. Min Act: -0.1700

Data Index: 1597763 (Open Web Text)

Max Activating Token Index: 80

Text #11

Max Range: 5.4610. Min Range: -5.4610

Max Act: 5.1997. Min Act: -0.1700

Data Index: 4954634 (Open Web Text)

Max Activating Token Index: 617

Text #12

Max Range: 5.4610. Min Range: -5.4610

Max Act: 5.1779. Min Act: -0.1700

Data Index: 3032615 (Open Web Text)

Max Activating Token Index: 348

Text #13

Max Range: 5.4610. Min Range: -5.4610

Max Act: 5.1021. Min Act: -0.1700

Data Index: 7491001 (Open Web Text)

Max Activating Token Index: 226

Text #14

Max Range: 5.4610. Min Range: -5.4610

Max Act: 5.1333. Min Act: -0.1700

Data Index: 357209 (Open Web Text)

Max Activating Token Index: 645

Text #15

Max Range: 5.4610. Min Range: -5.4610

Max Act: 5.1516. Min Act: -0.1700

Data Index: 897601 (Open Web Text)

Max Activating Token Index: 478

Text #16

Max Range: 5.4610. Min Range: -5.4610

Max Act: 5.1293. Min Act: -0.1700

Data Index: 7308311 (Open Web Text)

Max Activating Token Index: 484

Text #17

Max Range: 5.4610. Min Range: -5.4610

Max Act: 5.1264. Min Act: -0.1700

Data Index: 5727705 (Open Web Text)

Max Activating Token Index: 479

Text #18

Max Range: 5.4610. Min Range: -5.4610

Max Act: 5.1471. Min Act: -0.1700

Data Index: 2209000 (Open Web Text)

Max Activating Token Index: 813

Text #19

Max Range: 5.4610. Min Range: -5.4610

Max Act: 5.1197. Min Act: -0.1700

Data Index: 213121 (Open Web Text)

Max Activating Token Index: 118