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

Dataset: Open Web Text

Neuron 1393 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: 1.8576. Min Range: -1.8576

Max Act: 1.8576. Min Act: -0.1700

Data Index: 7697136 (Open Web Text)

Max Activating Token Index: 878

Text #1

Max Range: 1.8576. Min Range: -1.8576

Max Act: 1.8362. Min Act: -0.1700

Data Index: 2939834 (Open Web Text)

Max Activating Token Index: 464

Text #2

Max Range: 1.8576. Min Range: -1.8576

Max Act: 1.7927. Min Act: -0.1700

Data Index: 4406549 (Open Web Text)

Max Activating Token Index: 456

Text #3

Max Range: 1.8576. Min Range: -1.8576

Max Act: 1.7760. Min Act: -0.1699

Data Index: 6402691 (Open Web Text)

Max Activating Token Index: 13

Text #4

Max Range: 1.8576. Min Range: -1.8576

Max Act: 1.7696. Min Act: -0.1700

Data Index: 6448646 (Open Web Text)

Max Activating Token Index: 50

Text #5

Max Range: 1.8576. Min Range: -1.8576

Max Act: 1.7660. Min Act: -0.1700

Data Index: 6285632 (Open Web Text)

Max Activating Token Index: 168

Text #6

Max Range: 1.8576. Min Range: -1.8576

Max Act: 1.7639. Min Act: -0.1700

Data Index: 1061829 (Open Web Text)

Max Activating Token Index: 22

Text #7

Max Range: 1.8576. Min Range: -1.8576

Max Act: 1.7673. Min Act: -0.1700

Data Index: 6671594 (Open Web Text)

Max Activating Token Index: 165

Text #8

Max Range: 1.8576. Min Range: -1.8576

Max Act: 1.7597. Min Act: -0.1700

Data Index: 3485161 (Open Web Text)

Max Activating Token Index: 490

Text #9

Max Range: 1.8576. Min Range: -1.8576

Max Act: 1.7608. Min Act: -0.1700

Data Index: 10012 (Open Web Text)

Max Activating Token Index: 991

Text #10

Max Range: 1.8576. Min Range: -1.8576

Max Act: 1.7557. Min Act: -0.1699

Data Index: 2733233 (Open Web Text)

Max Activating Token Index: 333

Text #11

Max Range: 1.8576. Min Range: -1.8576

Max Act: 1.7505. Min Act: -0.1700

Data Index: 8454154 (Open Web Text)

Max Activating Token Index: 377

Text #12

Max Range: 1.8576. Min Range: -1.8576

Max Act: 1.7493. Min Act: -0.1700

Data Index: 431183 (Open Web Text)

Max Activating Token Index: 211

Text #13

Max Range: 1.8576. Min Range: -1.8576

Max Act: 1.7424. Min Act: -0.1700

Data Index: 6257400 (Open Web Text)

Max Activating Token Index: 782

Text #14

Max Range: 1.8576. Min Range: -1.8576

Max Act: 1.7491. Min Act: -0.1667

Data Index: 413590 (Open Web Text)

Max Activating Token Index: 593

Text #15

Max Range: 1.8576. Min Range: -1.8576

Max Act: 1.7442. Min Act: -0.1700

Data Index: 887691 (Open Web Text)

Max Activating Token Index: 1022

Text #16

Max Range: 1.8576. Min Range: -1.8576

Max Act: 1.7449. Min Act: -0.1700

Data Index: 8260360 (Open Web Text)

Max Activating Token Index: 257

Text #17

Max Range: 1.8576. Min Range: -1.8576

Max Act: 1.7348. Min Act: -0.1700

Data Index: 83142 (Open Web Text)

Max Activating Token Index: 358

Text #18

Max Range: 1.8576. Min Range: -1.8576

Max Act: 1.7425. Min Act: -0.1694

Data Index: 393937 (Open Web Text)

Max Activating Token Index: 570

Text #19

Max Range: 1.8576. Min Range: -1.8576

Max Act: 1.7218. Min Act: -0.1700

Data Index: 4165147 (Open Web Text)

Max Activating Token Index: 952