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

Dataset: Open Web Text

Neuron 2762 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: 1.5171. Min Range: -1.5171

Max Act: 1.5171. Min Act: -0.1700

Data Index: 8344511 (Open Web Text)

Max Activating Token Index: 100

Text #1

Max Range: 1.5171. Min Range: -1.5171

Max Act: 1.5036. Min Act: -0.1700

Data Index: 730244 (Open Web Text)

Max Activating Token Index: 664

Text #2

Max Range: 1.5171. Min Range: -1.5171

Max Act: 1.4859. Min Act: -0.1700

Data Index: 5216816 (Open Web Text)

Max Activating Token Index: 296

Text #3

Max Range: 1.5171. Min Range: -1.5171

Max Act: 1.4913. Min Act: -0.1700

Data Index: 1642403 (Open Web Text)

Max Activating Token Index: 449

Text #4

Max Range: 1.5171. Min Range: -1.5171

Max Act: 1.4759. Min Act: -0.1700

Data Index: 2716008 (Open Web Text)

Max Activating Token Index: 631

Text #5

Max Range: 1.5171. Min Range: -1.5171

Max Act: 1.4784. Min Act: -0.1700

Data Index: 8627478 (Open Web Text)

Max Activating Token Index: 654

Text #6

Max Range: 1.5171. Min Range: -1.5171

Max Act: 1.4742. Min Act: -0.1700

Data Index: 5306776 (Open Web Text)

Max Activating Token Index: 620

Text #7

Max Range: 1.5171. Min Range: -1.5171

Max Act: 1.4853. Min Act: -0.1700

Data Index: 3576773 (Open Web Text)

Max Activating Token Index: 558

Text #8

Max Range: 1.5171. Min Range: -1.5171

Max Act: 1.4644. Min Act: -0.1700

Data Index: 539344 (Open Web Text)

Max Activating Token Index: 27

Text #9

Max Range: 1.5171. Min Range: -1.5171

Max Act: 1.4751. Min Act: -0.1700

Data Index: 7192375 (Open Web Text)

Max Activating Token Index: 628

Text #10

Max Range: 1.5171. Min Range: -1.5171

Max Act: 1.4716. Min Act: -0.1700

Data Index: 3071565 (Open Web Text)

Max Activating Token Index: 978

Text #11

Max Range: 1.5171. Min Range: -1.5171

Max Act: 1.4741. Min Act: -0.1700

Data Index: 3983247 (Open Web Text)

Max Activating Token Index: 644

Text #12

Max Range: 1.5171. Min Range: -1.5171

Max Act: 1.4580. Min Act: -0.1700

Data Index: 8584378 (Open Web Text)

Max Activating Token Index: 30

Text #13

Max Range: 1.5171. Min Range: -1.5171

Max Act: 1.4608. Min Act: -0.1700

Data Index: 6272115 (Open Web Text)

Max Activating Token Index: 74

Text #14

Max Range: 1.5171. Min Range: -1.5171

Max Act: 1.4649. Min Act: -0.1700

Data Index: 8431836 (Open Web Text)

Max Activating Token Index: 390

Text #15

Max Range: 1.5171. Min Range: -1.5171

Max Act: 1.4614. Min Act: -0.1700

Data Index: 3744320 (Open Web Text)

Max Activating Token Index: 316

Text #16

Max Range: 1.5171. Min Range: -1.5171

Max Act: 1.4626. Min Act: -0.1700

Data Index: 828479 (Open Web Text)

Max Activating Token Index: 586

Text #17

Max Range: 1.5171. Min Range: -1.5171

Max Act: 1.4439. Min Act: -0.1700

Data Index: 7985688 (Open Web Text)

Max Activating Token Index: 26

Text #18

Max Range: 1.5171. Min Range: -1.5171

Max Act: 1.4544. Min Act: -0.1700

Data Index: 6541893 (Open Web Text)

Max Activating Token Index: 531

Text #19

Max Range: 1.5171. Min Range: -1.5171

Max Act: 1.4579. Min Act: -0.1700

Data Index: 6676565 (Open Web Text)

Max Activating Token Index: 320