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

Dataset: Open Web Text

Neuron 1305 in Layer 6

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: 5.0700. Min Range: -5.0700

Max Act: 5.0386. Min Act: -0.1700

Data Index: 1245148 (Open Web Text)

Max Activating Token Index: 778

Text #1

Max Range: 5.0700. Min Range: -5.0700

Max Act: 5.0502. Min Act: -0.1700

Data Index: 5055922 (Open Web Text)

Max Activating Token Index: 763

Text #2

Max Range: 5.0700. Min Range: -5.0700

Max Act: 5.0700. Min Act: -0.1700

Data Index: 6372761 (Open Web Text)

Max Activating Token Index: 275

Text #3

Max Range: 5.0700. Min Range: -5.0700

Max Act: 5.0489. Min Act: -0.1700

Data Index: 8493765 (Open Web Text)

Max Activating Token Index: 425

Text #4

Max Range: 5.0700. Min Range: -5.0700

Max Act: 5.0356. Min Act: -0.1700

Data Index: 1787387 (Open Web Text)

Max Activating Token Index: 1014

Text #5

Max Range: 5.0700. Min Range: -5.0700

Max Act: 4.9762. Min Act: -0.1700

Data Index: 4788268 (Open Web Text)

Max Activating Token Index: 572

Text #6

Max Range: 5.0700. Min Range: -5.0700

Max Act: 4.9916. Min Act: -0.1700

Data Index: 3825076 (Open Web Text)

Max Activating Token Index: 717

Text #7

Max Range: 5.0700. Min Range: -5.0700

Max Act: 4.9805. Min Act: -0.1700

Data Index: 6206046 (Open Web Text)

Max Activating Token Index: 944

Text #8

Max Range: 5.0700. Min Range: -5.0700

Max Act: 4.9501. Min Act: -0.1700

Data Index: 5051574 (Open Web Text)

Max Activating Token Index: 929

Text #9

Max Range: 5.0700. Min Range: -5.0700

Max Act: 4.9418. Min Act: -0.1700

Data Index: 8053427 (Open Web Text)

Max Activating Token Index: 525

Text #10

Max Range: 5.0700. Min Range: -5.0700

Max Act: 4.8975. Min Act: -0.1700

Data Index: 3291515 (Open Web Text)

Max Activating Token Index: 698

Text #11

Max Range: 5.0700. Min Range: -5.0700

Max Act: 4.9426. Min Act: -0.1700

Data Index: 2126788 (Open Web Text)

Max Activating Token Index: 71

Text #12

Max Range: 5.0700. Min Range: -5.0700

Max Act: 4.9277. Min Act: -0.1700

Data Index: 3175305 (Open Web Text)

Max Activating Token Index: 170

Text #13

Max Range: 5.0700. Min Range: -5.0700

Max Act: 4.9391. Min Act: -0.1700

Data Index: 8589458 (Open Web Text)

Max Activating Token Index: 771

Text #14

Max Range: 5.0700. Min Range: -5.0700

Max Act: 4.9308. Min Act: -0.1700

Data Index: 6236163 (Open Web Text)

Max Activating Token Index: 599

Text #15

Max Range: 5.0700. Min Range: -5.0700

Max Act: 4.9504. Min Act: -0.1700

Data Index: 3124075 (Open Web Text)

Max Activating Token Index: 586

Text #16

Max Range: 5.0700. Min Range: -5.0700

Max Act: 4.8759. Min Act: -0.1700

Data Index: 2604226 (Open Web Text)

Max Activating Token Index: 623

Text #17

Max Range: 5.0700. Min Range: -5.0700

Max Act: 4.8834. Min Act: -0.1700

Data Index: 4563583 (Open Web Text)

Max Activating Token Index: 381

Text #18

Max Range: 5.0700. Min Range: -5.0700

Max Act: 4.8802. Min Act: -0.1700

Data Index: 6654587 (Open Web Text)

Max Activating Token Index: 375

Text #19

Max Range: 5.0700. Min Range: -5.0700

Max Act: 4.8590. Min Act: -0.1700

Data Index: 6838468 (Open Web Text)

Max Activating Token Index: 302