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

Dataset: Open Web Text

Neuron 2025 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: 4.0916. Min Range: -4.0916

Max Act: 4.0916. Min Act: -0.1700

Data Index: 3726610 (Open Web Text)

Max Activating Token Index: 20

Text #1

Max Range: 4.0916. Min Range: -4.0916

Max Act: 4.0258. Min Act: -0.1700

Data Index: 5679678 (Open Web Text)

Max Activating Token Index: 510

Text #2

Max Range: 4.0916. Min Range: -4.0916

Max Act: 4.0289. Min Act: -0.1700

Data Index: 6131344 (Open Web Text)

Max Activating Token Index: 137

Text #3

Max Range: 4.0916. Min Range: -4.0916

Max Act: 4.0027. Min Act: -0.1700

Data Index: 8372212 (Open Web Text)

Max Activating Token Index: 87

Text #4

Max Range: 4.0916. Min Range: -4.0916

Max Act: 4.0022. Min Act: -0.1700

Data Index: 6101550 (Open Web Text)

Max Activating Token Index: 396

Text #5

Max Range: 4.0916. Min Range: -4.0916

Max Act: 3.9920. Min Act: -0.1700

Data Index: 6987616 (Open Web Text)

Max Activating Token Index: 738

Text #6

Max Range: 4.0916. Min Range: -4.0916

Max Act: 3.9618. Min Act: -0.1700

Data Index: 7299303 (Open Web Text)

Max Activating Token Index: 185

Text #7

Max Range: 4.0916. Min Range: -4.0916

Max Act: 4.0015. Min Act: -0.1700

Data Index: 990405 (Open Web Text)

Max Activating Token Index: 484

Text #8

Max Range: 4.0916. Min Range: -4.0916

Max Act: 3.9772. Min Act: -0.1700

Data Index: 4179543 (Open Web Text)

Max Activating Token Index: 529

Text #9

Max Range: 4.0916. Min Range: -4.0916

Max Act: 3.9389. Min Act: -0.1700

Data Index: 3701160 (Open Web Text)

Max Activating Token Index: 493

Text #10

Max Range: 4.0916. Min Range: -4.0916

Max Act: 3.9265. Min Act: -0.1700

Data Index: 6349283 (Open Web Text)

Max Activating Token Index: 41

Text #11

Max Range: 4.0916. Min Range: -4.0916

Max Act: 3.8920. Min Act: -0.1700

Data Index: 3936754 (Open Web Text)

Max Activating Token Index: 446

Text #12

Max Range: 4.0916. Min Range: -4.0916

Max Act: 3.9070. Min Act: -0.1700

Data Index: 8227334 (Open Web Text)

Max Activating Token Index: 17

Text #13

Max Range: 4.0916. Min Range: -4.0916

Max Act: 3.8821. Min Act: -0.1700

Data Index: 6200982 (Open Web Text)

Max Activating Token Index: 78

Text #14

Max Range: 4.0916. Min Range: -4.0916

Max Act: 3.9059. Min Act: -0.1700

Data Index: 5881478 (Open Web Text)

Max Activating Token Index: 234

Text #15

Max Range: 4.0916. Min Range: -4.0916

Max Act: 3.8718. Min Act: -0.1700

Data Index: 6242861 (Open Web Text)

Max Activating Token Index: 464

Text #16

Max Range: 4.0916. Min Range: -4.0916

Max Act: 3.8748. Min Act: -0.1700

Data Index: 1824633 (Open Web Text)

Max Activating Token Index: 444

Text #17

Max Range: 4.0916. Min Range: -4.0916

Max Act: 3.8627. Min Act: -0.1700

Data Index: 4327591 (Open Web Text)

Max Activating Token Index: 329

Text #18

Max Range: 4.0916. Min Range: -4.0916

Max Act: 3.8668. Min Act: -0.1700

Data Index: 4570497 (Open Web Text)

Max Activating Token Index: 130

Text #19

Max Range: 4.0916. Min Range: -4.0916

Max Act: 3.8508. Min Act: -0.1700

Data Index: 3428891 (Open Web Text)

Max Activating Token Index: 298