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

Dataset: Open Web Text

Neuron 2810 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: 5.8454. Min Range: -5.8454

Max Act: 5.8454. Min Act: -0.1700

Data Index: 7798306 (Open Web Text)

Max Activating Token Index: 272

Text #1

Max Range: 5.8454. Min Range: -5.8454

Max Act: 5.7730. Min Act: -0.1700

Data Index: 1124032 (Open Web Text)

Max Activating Token Index: 372

Text #2

Max Range: 5.8454. Min Range: -5.8454

Max Act: 5.7340. Min Act: -0.1700

Data Index: 1838455 (Open Web Text)

Max Activating Token Index: 692

Text #3

Max Range: 5.8454. Min Range: -5.8454

Max Act: 5.6317. Min Act: -0.1700

Data Index: 8108505 (Open Web Text)

Max Activating Token Index: 113

Text #4

Max Range: 5.8454. Min Range: -5.8454

Max Act: 5.6104. Min Act: -0.1700

Data Index: 3358320 (Open Web Text)

Max Activating Token Index: 715

Text #5

Max Range: 5.8454. Min Range: -5.8454

Max Act: 5.6214. Min Act: -0.1700

Data Index: 81704 (Open Web Text)

Max Activating Token Index: 282

Text #6

Max Range: 5.8454. Min Range: -5.8454

Max Act: 5.5536. Min Act: -0.1700

Data Index: 6513730 (Open Web Text)

Max Activating Token Index: 572

Text #7

Max Range: 5.8454. Min Range: -5.8454

Max Act: 5.5475. Min Act: -0.1700

Data Index: 3277607 (Open Web Text)

Max Activating Token Index: 120

Text #8

Max Range: 5.8454. Min Range: -5.8454

Max Act: 5.5299. Min Act: -0.1700

Data Index: 2992213 (Open Web Text)

Max Activating Token Index: 255

Text #9

Max Range: 5.8454. Min Range: -5.8454

Max Act: 5.5475. Min Act: -0.1700

Data Index: 7016315 (Open Web Text)

Max Activating Token Index: 821

Text #10

Max Range: 5.8454. Min Range: -5.8454

Max Act: 5.5599. Min Act: -0.1700

Data Index: 3584632 (Open Web Text)

Max Activating Token Index: 217

Text #11

Max Range: 5.8454. Min Range: -5.8454

Max Act: 5.5415. Min Act: -0.1700

Data Index: 7408477 (Open Web Text)

Max Activating Token Index: 465

Text #12

Max Range: 5.8454. Min Range: -5.8454

Max Act: 5.4959. Min Act: -0.1700

Data Index: 6480548 (Open Web Text)

Max Activating Token Index: 792

Text #13

Max Range: 5.8454. Min Range: -5.8454

Max Act: 5.5341. Min Act: -0.1700

Data Index: 8700090 (Open Web Text)

Max Activating Token Index: 165

Text #14

Max Range: 5.8454. Min Range: -5.8454

Max Act: 5.4980. Min Act: -0.1700

Data Index: 2261500 (Open Web Text)

Max Activating Token Index: 124

Text #15

Max Range: 5.8454. Min Range: -5.8454

Max Act: 5.4989. Min Act: -0.1700

Data Index: 2715499 (Open Web Text)

Max Activating Token Index: 329

Text #16

Max Range: 5.8454. Min Range: -5.8454

Max Act: 5.4885. Min Act: -0.1700

Data Index: 5505172 (Open Web Text)

Max Activating Token Index: 660

Text #17

Max Range: 5.8454. Min Range: -5.8454

Max Act: 5.4977. Min Act: -0.1700

Data Index: 472840 (Open Web Text)

Max Activating Token Index: 960

Text #18

Max Range: 5.8454. Min Range: -5.8454

Max Act: 5.4967. Min Act: -0.1700

Data Index: 7225878 (Open Web Text)

Max Activating Token Index: 416

Text #19

Max Range: 5.8454. Min Range: -5.8454

Max Act: 5.4615. Min Act: -0.1700

Data Index: 929725 (Open Web Text)

Max Activating Token Index: 706