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

Dataset: Open Web Text

Neuron 2135 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: 3.4819. Min Range: -3.4819

Max Act: 3.4819. Min Act: -0.1700

Data Index: 4093403 (Open Web Text)

Max Activating Token Index: 626

Text #1

Max Range: 3.4819. Min Range: -3.4819

Max Act: 3.4526. Min Act: -0.1700

Data Index: 531901 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 3.4819. Min Range: -3.4819

Max Act: 3.4739. Min Act: -0.1700

Data Index: 2754238 (Open Web Text)

Max Activating Token Index: 498

Text #3

Max Range: 3.4819. Min Range: -3.4819

Max Act: 3.4754. Min Act: -0.1700

Data Index: 8011531 (Open Web Text)

Max Activating Token Index: 654

Text #4

Max Range: 3.4819. Min Range: -3.4819

Max Act: 3.4713. Min Act: -0.1700

Data Index: 1823869 (Open Web Text)

Max Activating Token Index: 648

Text #5

Max Range: 3.4819. Min Range: -3.4819

Max Act: 3.4292. Min Act: -0.1700

Data Index: 2075292 (Open Web Text)

Max Activating Token Index: 1020

Text #6

Max Range: 3.4819. Min Range: -3.4819

Max Act: 3.4320. Min Act: -0.1700

Data Index: 1969054 (Open Web Text)

Max Activating Token Index: 352

Text #7

Max Range: 3.4819. Min Range: -3.4819

Max Act: 3.4200. Min Act: -0.1700

Data Index: 3414724 (Open Web Text)

Max Activating Token Index: 293

Text #8

Max Range: 3.4819. Min Range: -3.4819

Max Act: 3.4329. Min Act: -0.1700

Data Index: 4474003 (Open Web Text)

Max Activating Token Index: 56

Text #9

Max Range: 3.4819. Min Range: -3.4819

Max Act: 3.4024. Min Act: -0.1700

Data Index: 4212255 (Open Web Text)

Max Activating Token Index: 463

Text #10

Max Range: 3.4819. Min Range: -3.4819

Max Act: 3.4018. Min Act: -0.1700

Data Index: 7496159 (Open Web Text)

Max Activating Token Index: 437

Text #11

Max Range: 3.4819. Min Range: -3.4819

Max Act: 3.3850. Min Act: -0.1700

Data Index: 6695309 (Open Web Text)

Max Activating Token Index: 512

Text #12

Max Range: 3.4819. Min Range: -3.4819

Max Act: 3.4015. Min Act: -0.1700

Data Index: 1768915 (Open Web Text)

Max Activating Token Index: 235

Text #13

Max Range: 3.4819. Min Range: -3.4819

Max Act: 3.3860. Min Act: -0.1700

Data Index: 5419610 (Open Web Text)

Max Activating Token Index: 680

Text #14

Max Range: 3.4819. Min Range: -3.4819

Max Act: 3.4008. Min Act: -0.1700

Data Index: 3703655 (Open Web Text)

Max Activating Token Index: 985

Text #15

Max Range: 3.4819. Min Range: -3.4819

Max Act: 3.3885. Min Act: -0.1700

Data Index: 2826320 (Open Web Text)

Max Activating Token Index: 343

Text #16

Max Range: 3.4819. Min Range: -3.4819

Max Act: 3.3853. Min Act: -0.1700

Data Index: 7467213 (Open Web Text)

Max Activating Token Index: 658

Text #17

Max Range: 3.4819. Min Range: -3.4819

Max Act: 3.3932. Min Act: -0.1700

Data Index: 2952685 (Open Web Text)

Max Activating Token Index: 536

Text #18

Max Range: 3.4819. Min Range: -3.4819

Max Act: 3.3626. Min Act: -0.1700

Data Index: 31735 (Open Web Text)

Max Activating Token Index: 413

Text #19

Max Range: 3.4819. Min Range: -3.4819

Max Act: 3.3875. Min Act: -0.1700

Data Index: 587348 (Open Web Text)

Max Activating Token Index: 31