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

Dataset: Open Web Text

Neuron 270 in Layer 0

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: 0.9599. Min Range: -0.9599

Max Act: 0.9577. Min Act: -0.1700

Data Index: 3542792 (Open Web Text)

Max Activating Token Index: 849

Text #1

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.9599. Min Act: -0.1700

Data Index: 4712022 (Open Web Text)

Max Activating Token Index: 828

Text #2

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.9069. Min Act: -0.1700

Data Index: 1090900 (Open Web Text)

Max Activating Token Index: 800

Text #3

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.8937. Min Act: -0.1700

Data Index: 3316995 (Open Web Text)

Max Activating Token Index: 843

Text #4

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.8977. Min Act: -0.1700

Data Index: 5537256 (Open Web Text)

Max Activating Token Index: 881

Text #5

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.8727. Min Act: -0.1700

Data Index: 985085 (Open Web Text)

Max Activating Token Index: 944

Text #6

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.8739. Min Act: -0.1700

Data Index: 2287629 (Open Web Text)

Max Activating Token Index: 926

Text #7

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.8440. Min Act: -0.1700

Data Index: 5888225 (Open Web Text)

Max Activating Token Index: 975

Text #8

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.8387. Min Act: -0.1700

Data Index: 371914 (Open Web Text)

Max Activating Token Index: 832

Text #9

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.8551. Min Act: -0.1700

Data Index: 6466016 (Open Web Text)

Max Activating Token Index: 726

Text #10

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.8433. Min Act: -0.1700

Data Index: 7952796 (Open Web Text)

Max Activating Token Index: 841

Text #11

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.8181. Min Act: -0.1700

Data Index: 1338355 (Open Web Text)

Max Activating Token Index: 871

Text #12

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.8465. Min Act: -0.1700

Data Index: 3663329 (Open Web Text)

Max Activating Token Index: 751

Text #13

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.8372. Min Act: -0.1700

Data Index: 7950862 (Open Web Text)

Max Activating Token Index: 808

Text #14

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.8263. Min Act: -0.1700

Data Index: 8694882 (Open Web Text)

Max Activating Token Index: 807

Text #15

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.8513. Min Act: -0.1700

Data Index: 2514446 (Open Web Text)

Max Activating Token Index: 923

Text #16

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.8261. Min Act: -0.1700

Data Index: 756237 (Open Web Text)

Max Activating Token Index: 992

Text #17

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.8457. Min Act: -0.1700

Data Index: 438018 (Open Web Text)

Max Activating Token Index: 856

Text #18

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.8357. Min Act: -0.1700

Data Index: 1053580 (Open Web Text)

Max Activating Token Index: 818

Text #19

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.8317. Min Act: -0.1700

Data Index: 367495 (Open Web Text)

Max Activating Token Index: 850