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

Dataset: Open Web Text

Neuron 330 in Layer 5

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: 3.8538. Min Range: -3.8538

Max Act: 3.8223. Min Act: -0.1700

Data Index: 2363433 (Open Web Text)

Max Activating Token Index: 139

Text #1

Max Range: 3.8538. Min Range: -3.8538

Max Act: 3.8538. Min Act: -0.1700

Data Index: 6199292 (Open Web Text)

Max Activating Token Index: 686

Text #2

Max Range: 3.8538. Min Range: -3.8538

Max Act: 3.8071. Min Act: -0.1700

Data Index: 5934219 (Open Web Text)

Max Activating Token Index: 968

Text #3

Max Range: 3.8538. Min Range: -3.8538

Max Act: 3.7651. Min Act: -0.1700

Data Index: 8646767 (Open Web Text)

Max Activating Token Index: 640

Text #4

Max Range: 3.8538. Min Range: -3.8538

Max Act: 3.7323. Min Act: -0.1700

Data Index: 1182854 (Open Web Text)

Max Activating Token Index: 849

Text #5

Max Range: 3.8538. Min Range: -3.8538

Max Act: 3.7238. Min Act: -0.1700

Data Index: 7855684 (Open Web Text)

Max Activating Token Index: 420

Text #6

Max Range: 3.8538. Min Range: -3.8538

Max Act: 3.7426. Min Act: -0.1700

Data Index: 194829 (Open Web Text)

Max Activating Token Index: 594

Text #7

Max Range: 3.8538. Min Range: -3.8538

Max Act: 3.6959. Min Act: -0.1700

Data Index: 862640 (Open Web Text)

Max Activating Token Index: 306

Text #8

Max Range: 3.8538. Min Range: -3.8538

Max Act: 3.6573. Min Act: -0.1700

Data Index: 1833148 (Open Web Text)

Max Activating Token Index: 680

Text #9

Max Range: 3.8538. Min Range: -3.8538

Max Act: 3.6606. Min Act: -0.1700

Data Index: 5789969 (Open Web Text)

Max Activating Token Index: 565

Text #10

Max Range: 3.8538. Min Range: -3.8538

Max Act: 3.6627. Min Act: -0.1700

Data Index: 2713475 (Open Web Text)

Max Activating Token Index: 881

Text #11

Max Range: 3.8538. Min Range: -3.8538

Max Act: 3.6239. Min Act: -0.1700

Data Index: 2522275 (Open Web Text)

Max Activating Token Index: 627

Text #12

Max Range: 3.8538. Min Range: -3.8538

Max Act: 3.6679. Min Act: -0.1700

Data Index: 7562476 (Open Web Text)

Max Activating Token Index: 626

Text #13

Max Range: 3.8538. Min Range: -3.8538

Max Act: 3.6520. Min Act: -0.1700

Data Index: 749085 (Open Web Text)

Max Activating Token Index: 298

Text #14

Max Range: 3.8538. Min Range: -3.8538

Max Act: 3.6119. Min Act: -0.1700

Data Index: 4832392 (Open Web Text)

Max Activating Token Index: 896

Text #15

Max Range: 3.8538. Min Range: -3.8538

Max Act: 3.6334. Min Act: -0.1700

Data Index: 4052652 (Open Web Text)

Max Activating Token Index: 324

Text #16

Max Range: 3.8538. Min Range: -3.8538

Max Act: 3.6195. Min Act: -0.1700

Data Index: 1444658 (Open Web Text)

Max Activating Token Index: 645

Text #17

Max Range: 3.8538. Min Range: -3.8538

Max Act: 3.6068. Min Act: -0.1700

Data Index: 1147099 (Open Web Text)

Max Activating Token Index: 186

Text #18

Max Range: 3.8538. Min Range: -3.8538

Max Act: 3.5974. Min Act: -0.1700

Data Index: 5935144 (Open Web Text)

Max Activating Token Index: 100

Text #19

Max Range: 3.8538. Min Range: -3.8538

Max Act: 3.5974. Min Act: -0.1700

Data Index: 7962413 (Open Web Text)

Max Activating Token Index: 48