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

Dataset: Open Web Text

Neuron 1487 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: 1.7390. Min Range: -1.7390

Max Act: 1.7318. Min Act: -0.1700

Data Index: 764934 (Open Web Text)

Max Activating Token Index: 464

Text #1

Max Range: 1.7390. Min Range: -1.7390

Max Act: 1.7390. Min Act: -0.1700

Data Index: 3406458 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 1.7390. Min Range: -1.7390

Max Act: 1.7390. Min Act: -0.1700

Data Index: 7887904 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 1.7390. Min Range: -1.7390

Max Act: 1.7215. Min Act: -0.1700

Data Index: 3386207 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 1.7390. Min Range: -1.7390

Max Act: 1.6754. Min Act: -0.1700

Data Index: 8442481 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 1.7390. Min Range: -1.7390

Max Act: 1.6910. Min Act: -0.1700

Data Index: 661882 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 1.7390. Min Range: -1.7390

Max Act: 1.6787. Min Act: -0.1700

Data Index: 7234231 (Open Web Text)

Max Activating Token Index: 330

Text #7

Max Range: 1.7390. Min Range: -1.7390

Max Act: 1.6862. Min Act: -0.1700

Data Index: 910208 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 1.7390. Min Range: -1.7390

Max Act: 1.6622. Min Act: -0.1700

Data Index: 8362416 (Open Web Text)

Max Activating Token Index: 459

Text #9

Max Range: 1.7390. Min Range: -1.7390

Max Act: 1.6772. Min Act: -0.1700

Data Index: 1052236 (Open Web Text)

Max Activating Token Index: 420

Text #10

Max Range: 1.7390. Min Range: -1.7390

Max Act: 1.6586. Min Act: -0.1700

Data Index: 450124 (Open Web Text)

Max Activating Token Index: 408

Text #11

Max Range: 1.7390. Min Range: -1.7390

Max Act: 1.6629. Min Act: -0.1700

Data Index: 6509042 (Open Web Text)

Max Activating Token Index: 690

Text #12

Max Range: 1.7390. Min Range: -1.7390

Max Act: 1.6726. Min Act: -0.1700

Data Index: 8554413 (Open Web Text)

Max Activating Token Index: 386

Text #13

Max Range: 1.7390. Min Range: -1.7390

Max Act: 1.6522. Min Act: -0.1700

Data Index: 4504835 (Open Web Text)

Max Activating Token Index: 442

Text #14

Max Range: 1.7390. Min Range: -1.7390

Max Act: 1.6357. Min Act: -0.1700

Data Index: 3561446 (Open Web Text)

Max Activating Token Index: 13

Text #15

Max Range: 1.7390. Min Range: -1.7390

Max Act: 1.6680. Min Act: -0.1700

Data Index: 3580886 (Open Web Text)

Max Activating Token Index: 635

Text #16

Max Range: 1.7390. Min Range: -1.7390

Max Act: 1.6429. Min Act: -0.1700

Data Index: 7751340 (Open Web Text)

Max Activating Token Index: 452

Text #17

Max Range: 1.7390. Min Range: -1.7390

Max Act: 1.6498. Min Act: -0.1700

Data Index: 2886277 (Open Web Text)

Max Activating Token Index: 11

Text #18

Max Range: 1.7390. Min Range: -1.7390

Max Act: 1.6477. Min Act: -0.1700

Data Index: 4211005 (Open Web Text)

Max Activating Token Index: 217

Text #19

Max Range: 1.7390. Min Range: -1.7390

Max Act: 1.6450. Min Act: -0.1700

Data Index: 8090424 (Open Web Text)

Max Activating Token Index: 4