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

Dataset: Open Web Text

Neuron 1583 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: 3.7773. Min Range: -3.7773

Max Act: 3.7773. Min Act: -0.1700

Data Index: 2920357 (Open Web Text)

Max Activating Token Index: 946

Text #1

Max Range: 3.7773. Min Range: -3.7773

Max Act: 3.7622. Min Act: -0.1700

Data Index: 7225041 (Open Web Text)

Max Activating Token Index: 345

Text #2

Max Range: 3.7773. Min Range: -3.7773

Max Act: 3.7389. Min Act: -0.1700

Data Index: 7978262 (Open Web Text)

Max Activating Token Index: 821

Text #3

Max Range: 3.7773. Min Range: -3.7773

Max Act: 3.7219. Min Act: -0.1700

Data Index: 7549772 (Open Web Text)

Max Activating Token Index: 809

Text #4

Max Range: 3.7773. Min Range: -3.7773

Max Act: 3.6938. Min Act: -0.1700

Data Index: 6252368 (Open Web Text)

Max Activating Token Index: 553

Text #5

Max Range: 3.7773. Min Range: -3.7773

Max Act: 3.6746. Min Act: -0.1700

Data Index: 6360166 (Open Web Text)

Max Activating Token Index: 200

Text #6

Max Range: 3.7773. Min Range: -3.7773

Max Act: 3.6866. Min Act: -0.1700

Data Index: 6448577 (Open Web Text)

Max Activating Token Index: 467

Text #7

Max Range: 3.7773. Min Range: -3.7773

Max Act: 3.6542. Min Act: -0.1700

Data Index: 7550486 (Open Web Text)

Max Activating Token Index: 64

Text #8

Max Range: 3.7773. Min Range: -3.7773

Max Act: 3.6599. Min Act: -0.1700

Data Index: 1965443 (Open Web Text)

Max Activating Token Index: 317

Text #9

Max Range: 3.7773. Min Range: -3.7773

Max Act: 3.6236. Min Act: -0.1700

Data Index: 3497589 (Open Web Text)

Max Activating Token Index: 456

Text #10

Max Range: 3.7773. Min Range: -3.7773

Max Act: 3.6143. Min Act: -0.1700

Data Index: 3553279 (Open Web Text)

Max Activating Token Index: 963

Text #11

Max Range: 3.7773. Min Range: -3.7773

Max Act: 3.6029. Min Act: -0.1700

Data Index: 4256240 (Open Web Text)

Max Activating Token Index: 529

Text #12

Max Range: 3.7773. Min Range: -3.7773

Max Act: 3.6301. Min Act: -0.1700

Data Index: 7202207 (Open Web Text)

Max Activating Token Index: 398

Text #13

Max Range: 3.7773. Min Range: -3.7773

Max Act: 3.6191. Min Act: -0.1700

Data Index: 3936203 (Open Web Text)

Max Activating Token Index: 575

Text #14

Max Range: 3.7773. Min Range: -3.7773

Max Act: 3.5685. Min Act: -0.1700

Data Index: 3679690 (Open Web Text)

Max Activating Token Index: 939

Text #15

Max Range: 3.7773. Min Range: -3.7773

Max Act: 3.5472. Min Act: -0.1700

Data Index: 7409199 (Open Web Text)

Max Activating Token Index: 660

Text #16

Max Range: 3.7773. Min Range: -3.7773

Max Act: 3.5334. Min Act: -0.1700

Data Index: 981248 (Open Web Text)

Max Activating Token Index: 847

Text #17

Max Range: 3.7773. Min Range: -3.7773

Max Act: 3.5690. Min Act: -0.1700

Data Index: 3013280 (Open Web Text)

Max Activating Token Index: 390

Text #18

Max Range: 3.7773. Min Range: -3.7773

Max Act: 3.5754. Min Act: -0.1700

Data Index: 1226581 (Open Web Text)

Max Activating Token Index: 204

Text #19

Max Range: 3.7773. Min Range: -3.7773

Max Act: 3.5366. Min Act: -0.1700

Data Index: 7203740 (Open Web Text)

Max Activating Token Index: 847