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

Dataset: Open Web Text

Neuron 2821 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: 3.0869. Min Range: -3.0869

Max Act: 3.0869. Min Act: -0.1700

Data Index: 7669964 (Open Web Text)

Max Activating Token Index: 721

Text #1

Max Range: 3.0869. Min Range: -3.0869

Max Act: 3.0583. Min Act: -0.1700

Data Index: 3493132 (Open Web Text)

Max Activating Token Index: 405

Text #2

Max Range: 3.0869. Min Range: -3.0869

Max Act: 3.0145. Min Act: -0.1700

Data Index: 5858658 (Open Web Text)

Max Activating Token Index: 376

Text #3

Max Range: 3.0869. Min Range: -3.0869

Max Act: 2.9939. Min Act: -0.1700

Data Index: 8507692 (Open Web Text)

Max Activating Token Index: 629

Text #4

Max Range: 3.0869. Min Range: -3.0869

Max Act: 2.9694. Min Act: -0.1700

Data Index: 786080 (Open Web Text)

Max Activating Token Index: 222

Text #5

Max Range: 3.0869. Min Range: -3.0869

Max Act: 2.9617. Min Act: -0.1700

Data Index: 2986723 (Open Web Text)

Max Activating Token Index: 202

Text #6

Max Range: 3.0869. Min Range: -3.0869

Max Act: 2.9257. Min Act: -0.1700

Data Index: 2877431 (Open Web Text)

Max Activating Token Index: 234

Text #7

Max Range: 3.0869. Min Range: -3.0869

Max Act: 2.9444. Min Act: -0.1700

Data Index: 7348648 (Open Web Text)

Max Activating Token Index: 193

Text #8

Max Range: 3.0869. Min Range: -3.0869

Max Act: 2.9338. Min Act: -0.1700

Data Index: 1200938 (Open Web Text)

Max Activating Token Index: 568

Text #9

Max Range: 3.0869. Min Range: -3.0869

Max Act: 2.8689. Min Act: -0.1700

Data Index: 548 (Open Web Text)

Max Activating Token Index: 747

Text #10

Max Range: 3.0869. Min Range: -3.0869

Max Act: 2.8982. Min Act: -0.1700

Data Index: 6013963 (Open Web Text)

Max Activating Token Index: 177

Text #11

Max Range: 3.0869. Min Range: -3.0869

Max Act: 2.8887. Min Act: -0.1700

Data Index: 3493128 (Open Web Text)

Max Activating Token Index: 928

Text #12

Max Range: 3.0869. Min Range: -3.0869

Max Act: 2.8466. Min Act: -0.1700

Data Index: 936076 (Open Web Text)

Max Activating Token Index: 778

Text #13

Max Range: 3.0869. Min Range: -3.0869

Max Act: 2.9101. Min Act: -0.1700

Data Index: 4626446 (Open Web Text)

Max Activating Token Index: 285

Text #14

Max Range: 3.0869. Min Range: -3.0869

Max Act: 2.9011. Min Act: -0.1700

Data Index: 5022874 (Open Web Text)

Max Activating Token Index: 157

Text #15

Max Range: 3.0869. Min Range: -3.0869

Max Act: 2.8541. Min Act: -0.1700

Data Index: 3831682 (Open Web Text)

Max Activating Token Index: 918

Text #16

Max Range: 3.0869. Min Range: -3.0869

Max Act: 2.8711. Min Act: -0.1700

Data Index: 7896148 (Open Web Text)

Max Activating Token Index: 621

Text #17

Max Range: 3.0869. Min Range: -3.0869

Max Act: 2.8382. Min Act: -0.1700

Data Index: 40735 (Open Web Text)

Max Activating Token Index: 362

Text #18

Max Range: 3.0869. Min Range: -3.0869

Max Act: 2.8310. Min Act: -0.1700

Data Index: 4943309 (Open Web Text)

Max Activating Token Index: 652

Text #19

Max Range: 3.0869. Min Range: -3.0869

Max Act: 2.7977. Min Act: -0.1700

Data Index: 8768859 (Open Web Text)

Max Activating Token Index: 299