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

Dataset: Open Web Text

Neuron 2075 in Layer 6

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: 4.3417. Min Range: -4.3417

Max Act: 4.2996. Min Act: -0.1700

Data Index: 7393505 (Open Web Text)

Max Activating Token Index: 425

Text #1

Max Range: 4.3417. Min Range: -4.3417

Max Act: 4.3417. Min Act: -0.1700

Data Index: 2058244 (Open Web Text)

Max Activating Token Index: 137

Text #2

Max Range: 4.3417. Min Range: -4.3417

Max Act: 4.2720. Min Act: -0.1700

Data Index: 8312303 (Open Web Text)

Max Activating Token Index: 490

Text #3

Max Range: 4.3417. Min Range: -4.3417

Max Act: 4.1714. Min Act: -0.1700

Data Index: 1441940 (Open Web Text)

Max Activating Token Index: 315

Text #4

Max Range: 4.3417. Min Range: -4.3417

Max Act: 4.0942. Min Act: -0.1700

Data Index: 3566881 (Open Web Text)

Max Activating Token Index: 675

Text #5

Max Range: 4.3417. Min Range: -4.3417

Max Act: 4.1024. Min Act: -0.1700

Data Index: 6435951 (Open Web Text)

Max Activating Token Index: 701

Text #6

Max Range: 4.3417. Min Range: -4.3417

Max Act: 4.0815. Min Act: -0.1700

Data Index: 1449750 (Open Web Text)

Max Activating Token Index: 308

Text #7

Max Range: 4.3417. Min Range: -4.3417

Max Act: 4.0763. Min Act: -0.1700

Data Index: 4240384 (Open Web Text)

Max Activating Token Index: 472

Text #8

Max Range: 4.3417. Min Range: -4.3417

Max Act: 4.0440. Min Act: -0.1700

Data Index: 355770 (Open Web Text)

Max Activating Token Index: 441

Text #9

Max Range: 4.3417. Min Range: -4.3417

Max Act: 4.0792. Min Act: -0.1700

Data Index: 3351668 (Open Web Text)

Max Activating Token Index: 510

Text #10

Max Range: 4.3417. Min Range: -4.3417

Max Act: 4.0231. Min Act: -0.1700

Data Index: 449013 (Open Web Text)

Max Activating Token Index: 791

Text #11

Max Range: 4.3417. Min Range: -4.3417

Max Act: 3.9930. Min Act: -0.1700

Data Index: 659389 (Open Web Text)

Max Activating Token Index: 268

Text #12

Max Range: 4.3417. Min Range: -4.3417

Max Act: 4.0099. Min Act: -0.1700

Data Index: 5228274 (Open Web Text)

Max Activating Token Index: 860

Text #13

Max Range: 4.3417. Min Range: -4.3417

Max Act: 4.0048. Min Act: -0.1700

Data Index: 3013715 (Open Web Text)

Max Activating Token Index: 653

Text #14

Max Range: 4.3417. Min Range: -4.3417

Max Act: 3.9925. Min Act: -0.1700

Data Index: 3943861 (Open Web Text)

Max Activating Token Index: 507

Text #15

Max Range: 4.3417. Min Range: -4.3417

Max Act: 4.0153. Min Act: -0.1700

Data Index: 382916 (Open Web Text)

Max Activating Token Index: 667

Text #16

Max Range: 4.3417. Min Range: -4.3417

Max Act: 3.9986. Min Act: -0.1700

Data Index: 4623225 (Open Web Text)

Max Activating Token Index: 456

Text #17

Max Range: 4.3417. Min Range: -4.3417

Max Act: 4.0010. Min Act: -0.1700

Data Index: 1019746 (Open Web Text)

Max Activating Token Index: 656

Text #18

Max Range: 4.3417. Min Range: -4.3417

Max Act: 3.9968. Min Act: -0.1700

Data Index: 2308744 (Open Web Text)

Max Activating Token Index: 575

Text #19

Max Range: 4.3417. Min Range: -4.3417

Max Act: 3.9981. Min Act: -0.1700

Data Index: 3903885 (Open Web Text)

Max Activating Token Index: 749