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

Dataset: Open Web Text

Neuron 1531 in Layer 0

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: 4.4738. Min Range: -4.4738

Max Act: 4.4738. Min Act: -0.1700

Data Index: 5479188 (Open Web Text)

Max Activating Token Index: 468

Text #1

Max Range: 4.4738. Min Range: -4.4738

Max Act: 4.3815. Min Act: -0.1698

Data Index: 4645844 (Open Web Text)

Max Activating Token Index: 382

Text #2

Max Range: 4.4738. Min Range: -4.4738

Max Act: 4.3422. Min Act: -0.1698

Data Index: 4645845 (Open Web Text)

Max Activating Token Index: 51

Text #3

Max Range: 4.4738. Min Range: -4.4738

Max Act: 4.3282. Min Act: -0.1700

Data Index: 252690 (Open Web Text)

Max Activating Token Index: 791

Text #4

Max Range: 4.4738. Min Range: -4.4738

Max Act: 4.2179. Min Act: -0.1676

Data Index: 8352603 (Open Web Text)

Max Activating Token Index: 202

Text #5

Max Range: 4.4738. Min Range: -4.4738

Max Act: 4.0206. Min Act: -0.1700

Data Index: 4204640 (Open Web Text)

Max Activating Token Index: 63

Text #6

Max Range: 4.4738. Min Range: -4.4738

Max Act: 4.0446. Min Act: -0.1700

Data Index: 7579237 (Open Web Text)

Max Activating Token Index: 47

Text #7

Max Range: 4.4738. Min Range: -4.4738

Max Act: 4.0170. Min Act: -0.1698

Data Index: 1027509 (Open Web Text)

Max Activating Token Index: 882

Text #8

Max Range: 4.4738. Min Range: -4.4738

Max Act: 3.9969. Min Act: -0.1698

Data Index: 2409367 (Open Web Text)

Max Activating Token Index: 130

Text #9

Max Range: 4.4738. Min Range: -4.4738

Max Act: 3.9949. Min Act: -0.1700

Data Index: 5509848 (Open Web Text)

Max Activating Token Index: 860

Text #10

Max Range: 4.4738. Min Range: -4.4738

Max Act: 3.9719. Min Act: -0.1698

Data Index: 2409380 (Open Web Text)

Max Activating Token Index: 681

Text #11

Max Range: 4.4738. Min Range: -4.4738

Max Act: 3.9161. Min Act: -0.1700

Data Index: 3597667 (Open Web Text)

Max Activating Token Index: 829

Text #12

Max Range: 4.4738. Min Range: -4.4738

Max Act: 3.9328. Min Act: -0.1700

Data Index: 625173 (Open Web Text)

Max Activating Token Index: 175

Text #13

Max Range: 4.4738. Min Range: -4.4738

Max Act: 3.8853. Min Act: -0.1659

Data Index: 3175978 (Open Web Text)

Max Activating Token Index: 373

Text #14

Max Range: 4.4738. Min Range: -4.4738

Max Act: 3.8982. Min Act: -0.1700

Data Index: 6158688 (Open Web Text)

Max Activating Token Index: 657

Text #15

Max Range: 4.4738. Min Range: -4.4738

Max Act: 3.8856. Min Act: -0.1700

Data Index: 6973375 (Open Web Text)

Max Activating Token Index: 353

Text #16

Max Range: 4.4738. Min Range: -4.4738

Max Act: 3.8896. Min Act: -0.1700

Data Index: 749024 (Open Web Text)

Max Activating Token Index: 190

Text #17

Max Range: 4.4738. Min Range: -4.4738

Max Act: 3.8608. Min Act: -0.1639

Data Index: 4560814 (Open Web Text)

Max Activating Token Index: 396

Text #18

Max Range: 4.4738. Min Range: -4.4738

Max Act: 3.8600. Min Act: -0.1700

Data Index: 4863807 (Open Web Text)

Max Activating Token Index: 64

Text #19

Max Range: 4.4738. Min Range: -4.4738

Max Act: 3.8674. Min Act: -0.1700

Data Index: 6791445 (Open Web Text)

Max Activating Token Index: 382