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

Dataset: Open Web Text

Neuron 550 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: 4.6215. Min Range: -4.6215

Max Act: 4.6215. Min Act: -0.1700

Data Index: 745205 (Open Web Text)

Max Activating Token Index: 373

Text #1

Max Range: 4.6215. Min Range: -4.6215

Max Act: 4.6099. Min Act: -0.1700

Data Index: 8274623 (Open Web Text)

Max Activating Token Index: 334

Text #2

Max Range: 4.6215. Min Range: -4.6215

Max Act: 4.5852. Min Act: -0.1700

Data Index: 3648407 (Open Web Text)

Max Activating Token Index: 204

Text #3

Max Range: 4.6215. Min Range: -4.6215

Max Act: 4.5559. Min Act: -0.1700

Data Index: 2144263 (Open Web Text)

Max Activating Token Index: 301

Text #4

Max Range: 4.6215. Min Range: -4.6215

Max Act: 4.5530. Min Act: -0.1700

Data Index: 5811427 (Open Web Text)

Max Activating Token Index: 827

Text #5

Max Range: 4.6215. Min Range: -4.6215

Max Act: 4.5412. Min Act: -0.1700

Data Index: 8298129 (Open Web Text)

Max Activating Token Index: 390

Text #6

Max Range: 4.6215. Min Range: -4.6215

Max Act: 4.5323. Min Act: -0.1700

Data Index: 3169037 (Open Web Text)

Max Activating Token Index: 375

Text #7

Max Range: 4.6215. Min Range: -4.6215

Max Act: 4.5047. Min Act: -0.1700

Data Index: 1209910 (Open Web Text)

Max Activating Token Index: 209

Text #8

Max Range: 4.6215. Min Range: -4.6215

Max Act: 4.5044. Min Act: -0.1700

Data Index: 6604077 (Open Web Text)

Max Activating Token Index: 213

Text #9

Max Range: 4.6215. Min Range: -4.6215

Max Act: 4.4976. Min Act: -0.1700

Data Index: 5288476 (Open Web Text)

Max Activating Token Index: 325

Text #10

Max Range: 4.6215. Min Range: -4.6215

Max Act: 4.4975. Min Act: -0.1700

Data Index: 1112133 (Open Web Text)

Max Activating Token Index: 779

Text #11

Max Range: 4.6215. Min Range: -4.6215

Max Act: 4.5011. Min Act: -0.1700

Data Index: 3023999 (Open Web Text)

Max Activating Token Index: 405

Text #12

Max Range: 4.6215. Min Range: -4.6215

Max Act: 4.5155. Min Act: -0.1700

Data Index: 2762993 (Open Web Text)

Max Activating Token Index: 506

Text #13

Max Range: 4.6215. Min Range: -4.6215

Max Act: 4.5102. Min Act: -0.1700

Data Index: 7952115 (Open Web Text)

Max Activating Token Index: 534

Text #14

Max Range: 4.6215. Min Range: -4.6215

Max Act: 4.4883. Min Act: -0.1700

Data Index: 6963748 (Open Web Text)

Max Activating Token Index: 651

Text #15

Max Range: 4.6215. Min Range: -4.6215

Max Act: 4.5384. Min Act: -0.1700

Data Index: 672787 (Open Web Text)

Max Activating Token Index: 280

Text #16

Max Range: 4.6215. Min Range: -4.6215

Max Act: 4.5122. Min Act: -0.1700

Data Index: 655854 (Open Web Text)

Max Activating Token Index: 724

Text #17

Max Range: 4.6215. Min Range: -4.6215

Max Act: 4.5046. Min Act: -0.1700

Data Index: 6882695 (Open Web Text)

Max Activating Token Index: 433

Text #18

Max Range: 4.6215. Min Range: -4.6215

Max Act: 4.4840. Min Act: -0.1700

Data Index: 3903698 (Open Web Text)

Max Activating Token Index: 433

Text #19

Max Range: 4.6215. Min Range: -4.6215

Max Act: 4.4823. Min Act: -0.1700

Data Index: 4612388 (Open Web Text)

Max Activating Token Index: 58