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

Dataset: Open Web Text

Neuron 1779 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: 4.5743. Min Range: -4.5743

Max Act: 4.5743. Min Act: -0.1700

Data Index: 7096900 (Open Web Text)

Max Activating Token Index: 653

Text #1

Max Range: 4.5743. Min Range: -4.5743

Max Act: 4.3607. Min Act: -0.1700

Data Index: 1574125 (Open Web Text)

Max Activating Token Index: 67

Text #2

Max Range: 4.5743. Min Range: -4.5743

Max Act: 4.3467. Min Act: -0.1700

Data Index: 4414872 (Open Web Text)

Max Activating Token Index: 887

Text #3

Max Range: 4.5743. Min Range: -4.5743

Max Act: 4.3662. Min Act: -0.1700

Data Index: 5489061 (Open Web Text)

Max Activating Token Index: 75

Text #4

Max Range: 4.5743. Min Range: -4.5743

Max Act: 4.2771. Min Act: -0.1700

Data Index: 4330966 (Open Web Text)

Max Activating Token Index: 125

Text #5

Max Range: 4.5743. Min Range: -4.5743

Max Act: 4.3154. Min Act: -0.1700

Data Index: 1799257 (Open Web Text)

Max Activating Token Index: 493

Text #6

Max Range: 4.5743. Min Range: -4.5743

Max Act: 4.2620. Min Act: -0.1700

Data Index: 5240762 (Open Web Text)

Max Activating Token Index: 72

Text #7

Max Range: 4.5743. Min Range: -4.5743

Max Act: 4.2166. Min Act: -0.1700

Data Index: 2526793 (Open Web Text)

Max Activating Token Index: 212

Text #8

Max Range: 4.5743. Min Range: -4.5743

Max Act: 4.1869. Min Act: -0.1700

Data Index: 721828 (Open Web Text)

Max Activating Token Index: 779

Text #9

Max Range: 4.5743. Min Range: -4.5743

Max Act: 4.1865. Min Act: -0.1700

Data Index: 977990 (Open Web Text)

Max Activating Token Index: 413

Text #10

Max Range: 4.5743. Min Range: -4.5743

Max Act: 4.2021. Min Act: -0.1700

Data Index: 5247002 (Open Web Text)

Max Activating Token Index: 335

Text #11

Max Range: 4.5743. Min Range: -4.5743

Max Act: 4.1685. Min Act: -0.1700

Data Index: 2042115 (Open Web Text)

Max Activating Token Index: 765

Text #12

Max Range: 4.5743. Min Range: -4.5743

Max Act: 4.1955. Min Act: -0.1700

Data Index: 2171398 (Open Web Text)

Max Activating Token Index: 849

Text #13

Max Range: 4.5743. Min Range: -4.5743

Max Act: 4.1999. Min Act: -0.1700

Data Index: 22871 (Open Web Text)

Max Activating Token Index: 992

Text #14

Max Range: 4.5743. Min Range: -4.5743

Max Act: 4.1473. Min Act: -0.1700

Data Index: 4006959 (Open Web Text)

Max Activating Token Index: 266

Text #15

Max Range: 4.5743. Min Range: -4.5743

Max Act: 4.1596. Min Act: -0.1700

Data Index: 4143063 (Open Web Text)

Max Activating Token Index: 248

Text #16

Max Range: 4.5743. Min Range: -4.5743

Max Act: 4.1766. Min Act: -0.1700

Data Index: 4362807 (Open Web Text)

Max Activating Token Index: 490

Text #17

Max Range: 4.5743. Min Range: -4.5743

Max Act: 4.1670. Min Act: -0.1700

Data Index: 1716443 (Open Web Text)

Max Activating Token Index: 459

Text #18

Max Range: 4.5743. Min Range: -4.5743

Max Act: 4.1711. Min Act: -0.1700

Data Index: 1743698 (Open Web Text)

Max Activating Token Index: 579

Text #19

Max Range: 4.5743. Min Range: -4.5743

Max Act: 4.1453. Min Act: -0.1700

Data Index: 237858 (Open Web Text)

Max Activating Token Index: 898