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

Dataset: Open Web Text

Neuron 1326 in Layer 1

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: 5.0589. Min Range: -5.0589

Max Act: 5.0589. Min Act: -0.1700

Data Index: 5744634 (Open Web Text)

Max Activating Token Index: 398

Text #1

Max Range: 5.0589. Min Range: -5.0589

Max Act: 5.0413. Min Act: -0.1700

Data Index: 8701973 (Open Web Text)

Max Activating Token Index: 13

Text #2

Max Range: 5.0589. Min Range: -5.0589

Max Act: 5.0319. Min Act: -0.1700

Data Index: 6663562 (Open Web Text)

Max Activating Token Index: 373

Text #3

Max Range: 5.0589. Min Range: -5.0589

Max Act: 5.0484. Min Act: -0.1700

Data Index: 813829 (Open Web Text)

Max Activating Token Index: 152

Text #4

Max Range: 5.0589. Min Range: -5.0589

Max Act: 5.0121. Min Act: -0.1700

Data Index: 2418753 (Open Web Text)

Max Activating Token Index: 48

Text #5

Max Range: 5.0589. Min Range: -5.0589

Max Act: 5.0093. Min Act: -0.1700

Data Index: 8246937 (Open Web Text)

Max Activating Token Index: 490

Text #6

Max Range: 5.0589. Min Range: -5.0589

Max Act: 5.0178. Min Act: -0.1700

Data Index: 1903967 (Open Web Text)

Max Activating Token Index: 252

Text #7

Max Range: 5.0589. Min Range: -5.0589

Max Act: 5.0168. Min Act: -0.1700

Data Index: 7744141 (Open Web Text)

Max Activating Token Index: 213

Text #8

Max Range: 5.0589. Min Range: -5.0589

Max Act: 5.0202. Min Act: -0.1700

Data Index: 1827768 (Open Web Text)

Max Activating Token Index: 97

Text #9

Max Range: 5.0589. Min Range: -5.0589

Max Act: 4.9806. Min Act: -0.1700

Data Index: 7004526 (Open Web Text)

Max Activating Token Index: 455

Text #10

Max Range: 5.0589. Min Range: -5.0589

Max Act: 4.9719. Min Act: -0.1700

Data Index: 3596687 (Open Web Text)

Max Activating Token Index: 381

Text #11

Max Range: 5.0589. Min Range: -5.0589

Max Act: 4.9996. Min Act: -0.1700

Data Index: 1089861 (Open Web Text)

Max Activating Token Index: 92

Text #12

Max Range: 5.0589. Min Range: -5.0589

Max Act: 4.9956. Min Act: -0.1700

Data Index: 736419 (Open Web Text)

Max Activating Token Index: 177

Text #13

Max Range: 5.0589. Min Range: -5.0589

Max Act: 4.9838. Min Act: -0.1700

Data Index: 3115865 (Open Web Text)

Max Activating Token Index: 321

Text #14

Max Range: 5.0589. Min Range: -5.0589

Max Act: 4.9927. Min Act: -0.1700

Data Index: 5340773 (Open Web Text)

Max Activating Token Index: 128

Text #15

Max Range: 5.0589. Min Range: -5.0589

Max Act: 4.9498. Min Act: -0.1700

Data Index: 4463335 (Open Web Text)

Max Activating Token Index: 172

Text #16

Max Range: 5.0589. Min Range: -5.0589

Max Act: 4.9649. Min Act: -0.1700

Data Index: 4481849 (Open Web Text)

Max Activating Token Index: 494

Text #17

Max Range: 5.0589. Min Range: -5.0589

Max Act: 4.9735. Min Act: -0.1700

Data Index: 4693297 (Open Web Text)

Max Activating Token Index: 603

Text #18

Max Range: 5.0589. Min Range: -5.0589

Max Act: 4.9755. Min Act: -0.1700

Data Index: 2968904 (Open Web Text)

Max Activating Token Index: 217

Text #19

Max Range: 5.0589. Min Range: -5.0589

Max Act: 4.9496. Min Act: -0.1700

Data Index: 5495678 (Open Web Text)

Max Activating Token Index: 78