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

Dataset: Open Web Text

Neuron 1863 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: 4.5821. Min Range: -4.5821

Max Act: 4.5821. Min Act: -0.1700

Data Index: 2492176 (Open Web Text)

Max Activating Token Index: 687

Text #1

Max Range: 4.5821. Min Range: -4.5821

Max Act: 4.5705. Min Act: -0.1700

Data Index: 5775612 (Open Web Text)

Max Activating Token Index: 180

Text #2

Max Range: 4.5821. Min Range: -4.5821

Max Act: 4.5815. Min Act: -0.1700

Data Index: 2833185 (Open Web Text)

Max Activating Token Index: 323

Text #3

Max Range: 4.5821. Min Range: -4.5821

Max Act: 4.5446. Min Act: -0.1700

Data Index: 8677996 (Open Web Text)

Max Activating Token Index: 633

Text #4

Max Range: 4.5821. Min Range: -4.5821

Max Act: 4.5264. Min Act: -0.1700

Data Index: 8715475 (Open Web Text)

Max Activating Token Index: 247

Text #5

Max Range: 4.5821. Min Range: -4.5821

Max Act: 4.5334. Min Act: -0.1700

Data Index: 6561735 (Open Web Text)

Max Activating Token Index: 324

Text #6

Max Range: 4.5821. Min Range: -4.5821

Max Act: 4.5521. Min Act: -0.1700

Data Index: 3554725 (Open Web Text)

Max Activating Token Index: 110

Text #7

Max Range: 4.5821. Min Range: -4.5821

Max Act: 4.5504. Min Act: -0.1700

Data Index: 680198 (Open Web Text)

Max Activating Token Index: 261

Text #8

Max Range: 4.5821. Min Range: -4.5821

Max Act: 4.5109. Min Act: -0.1700

Data Index: 5811145 (Open Web Text)

Max Activating Token Index: 141

Text #9

Max Range: 4.5821. Min Range: -4.5821

Max Act: 4.5003. Min Act: -0.1700

Data Index: 259946 (Open Web Text)

Max Activating Token Index: 351

Text #10

Max Range: 4.5821. Min Range: -4.5821

Max Act: 4.4971. Min Act: -0.1700

Data Index: 5584895 (Open Web Text)

Max Activating Token Index: 209

Text #11

Max Range: 4.5821. Min Range: -4.5821

Max Act: 4.5198. Min Act: -0.1700

Data Index: 5235056 (Open Web Text)

Max Activating Token Index: 165

Text #12

Max Range: 4.5821. Min Range: -4.5821

Max Act: 4.5078. Min Act: -0.1700

Data Index: 4817331 (Open Web Text)

Max Activating Token Index: 863

Text #13

Max Range: 4.5821. Min Range: -4.5821

Max Act: 4.4843. Min Act: -0.1700

Data Index: 2714785 (Open Web Text)

Max Activating Token Index: 351

Text #14

Max Range: 4.5821. Min Range: -4.5821

Max Act: 4.5098. Min Act: -0.1700

Data Index: 996048 (Open Web Text)

Max Activating Token Index: 377

Text #15

Max Range: 4.5821. Min Range: -4.5821

Max Act: 4.5007. Min Act: -0.1700

Data Index: 4364761 (Open Web Text)

Max Activating Token Index: 389

Text #16

Max Range: 4.5821. Min Range: -4.5821

Max Act: 4.5143. Min Act: -0.1700

Data Index: 4232542 (Open Web Text)

Max Activating Token Index: 232

Text #17

Max Range: 4.5821. Min Range: -4.5821

Max Act: 4.5012. Min Act: -0.1700

Data Index: 4205590 (Open Web Text)

Max Activating Token Index: 753

Text #18

Max Range: 4.5821. Min Range: -4.5821

Max Act: 4.5213. Min Act: -0.1700

Data Index: 3789710 (Open Web Text)

Max Activating Token Index: 383

Text #19

Max Range: 4.5821. Min Range: -4.5821

Max Act: 4.5120. Min Act: -0.1700

Data Index: 3496288 (Open Web Text)

Max Activating Token Index: 309