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

Dataset: Open Web Text

Neuron 538 in Layer 3

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: 2.1540. Min Range: -2.1540

Max Act: 2.1540. Min Act: -0.1700

Data Index: 8460779 (Open Web Text)

Max Activating Token Index: 722

Text #1

Max Range: 2.1540. Min Range: -2.1540

Max Act: 2.1386. Min Act: -0.1700

Data Index: 8460778 (Open Web Text)

Max Activating Token Index: 741

Text #2

Max Range: 2.1540. Min Range: -2.1540

Max Act: 2.1139. Min Act: -0.1700

Data Index: 4560271 (Open Web Text)

Max Activating Token Index: 656

Text #3

Max Range: 2.1540. Min Range: -2.1540

Max Act: 2.0983. Min Act: -0.1700

Data Index: 1509484 (Open Web Text)

Max Activating Token Index: 20

Text #4

Max Range: 2.1540. Min Range: -2.1540

Max Act: 2.0637. Min Act: -0.1700

Data Index: 7421075 (Open Web Text)

Max Activating Token Index: 607

Text #5

Max Range: 2.1540. Min Range: -2.1540

Max Act: 2.0603. Min Act: -0.1700

Data Index: 7567233 (Open Web Text)

Max Activating Token Index: 351

Text #6

Max Range: 2.1540. Min Range: -2.1540

Max Act: 2.0372. Min Act: -0.1700

Data Index: 5178616 (Open Web Text)

Max Activating Token Index: 854

Text #7

Max Range: 2.1540. Min Range: -2.1540

Max Act: 2.0596. Min Act: -0.1700

Data Index: 4379323 (Open Web Text)

Max Activating Token Index: 196

Text #8

Max Range: 2.1540. Min Range: -2.1540

Max Act: 2.0181. Min Act: -0.1700

Data Index: 1284255 (Open Web Text)

Max Activating Token Index: 621

Text #9

Max Range: 2.1540. Min Range: -2.1540

Max Act: 2.0279. Min Act: -0.1700

Data Index: 2568205 (Open Web Text)

Max Activating Token Index: 174

Text #10

Max Range: 2.1540. Min Range: -2.1540

Max Act: 2.0174. Min Act: -0.1700

Data Index: 8662974 (Open Web Text)

Max Activating Token Index: 928

Text #11

Max Range: 2.1540. Min Range: -2.1540

Max Act: 2.0152. Min Act: -0.1700

Data Index: 5093403 (Open Web Text)

Max Activating Token Index: 1010

Text #12

Max Range: 2.1540. Min Range: -2.1540

Max Act: 1.9964. Min Act: -0.1700

Data Index: 1743902 (Open Web Text)

Max Activating Token Index: 23

Text #13

Max Range: 2.1540. Min Range: -2.1540

Max Act: 1.9949. Min Act: -0.1700

Data Index: 7233795 (Open Web Text)

Max Activating Token Index: 448

Text #14

Max Range: 2.1540. Min Range: -2.1540

Max Act: 2.0080. Min Act: -0.1700

Data Index: 4701493 (Open Web Text)

Max Activating Token Index: 191

Text #15

Max Range: 2.1540. Min Range: -2.1540

Max Act: 1.9945. Min Act: -0.1700

Data Index: 8798187 (Open Web Text)

Max Activating Token Index: 594

Text #16

Max Range: 2.1540. Min Range: -2.1540

Max Act: 1.9808. Min Act: -0.1700

Data Index: 3919370 (Open Web Text)

Max Activating Token Index: 552

Text #17

Max Range: 2.1540. Min Range: -2.1540

Max Act: 1.9880. Min Act: -0.1700

Data Index: 3691543 (Open Web Text)

Max Activating Token Index: 793

Text #18

Max Range: 2.1540. Min Range: -2.1540

Max Act: 1.9751. Min Act: -0.1700

Data Index: 4629172 (Open Web Text)

Max Activating Token Index: 84

Text #19

Max Range: 2.1540. Min Range: -2.1540

Max Act: 1.9748. Min Act: -0.1700

Data Index: 3016719 (Open Web Text)

Max Activating Token Index: 843