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

Dataset: Open Web Text

Neuron 2051 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: 4.0655. Min Range: -4.0655

Max Act: 4.0584. Min Act: -0.1700

Data Index: 8144437 (Open Web Text)

Max Activating Token Index: 968

Text #1

Max Range: 4.0655. Min Range: -4.0655

Max Act: 4.0280. Min Act: -0.1700

Data Index: 2746827 (Open Web Text)

Max Activating Token Index: 987

Text #2

Max Range: 4.0655. Min Range: -4.0655

Max Act: 4.0599. Min Act: -0.1700

Data Index: 2746828 (Open Web Text)

Max Activating Token Index: 42

Text #3

Max Range: 4.0655. Min Range: -4.0655

Max Act: 4.0655. Min Act: -0.1700

Data Index: 6821017 (Open Web Text)

Max Activating Token Index: 50

Text #4

Max Range: 4.0655. Min Range: -4.0655

Max Act: 4.0269. Min Act: -0.1700

Data Index: 4620842 (Open Web Text)

Max Activating Token Index: 552

Text #5

Max Range: 4.0655. Min Range: -4.0655

Max Act: 4.0310. Min Act: -0.1700

Data Index: 2404241 (Open Web Text)

Max Activating Token Index: 931

Text #6

Max Range: 4.0655. Min Range: -4.0655

Max Act: 4.0172. Min Act: -0.1700

Data Index: 6105643 (Open Web Text)

Max Activating Token Index: 145

Text #7

Max Range: 4.0655. Min Range: -4.0655

Max Act: 3.9883. Min Act: -0.1700

Data Index: 4431927 (Open Web Text)

Max Activating Token Index: 618

Text #8

Max Range: 4.0655. Min Range: -4.0655

Max Act: 4.0053. Min Act: -0.1700

Data Index: 5600236 (Open Web Text)

Max Activating Token Index: 34

Text #9

Max Range: 4.0655. Min Range: -4.0655

Max Act: 4.0047. Min Act: -0.1700

Data Index: 1457243 (Open Web Text)

Max Activating Token Index: 563

Text #10

Max Range: 4.0655. Min Range: -4.0655

Max Act: 4.0152. Min Act: -0.1700

Data Index: 1540911 (Open Web Text)

Max Activating Token Index: 205

Text #11

Max Range: 4.0655. Min Range: -4.0655

Max Act: 3.9929. Min Act: -0.1700

Data Index: 427560 (Open Web Text)

Max Activating Token Index: 319

Text #12

Max Range: 4.0655. Min Range: -4.0655

Max Act: 3.9934. Min Act: -0.1700

Data Index: 3579427 (Open Web Text)

Max Activating Token Index: 307

Text #13

Max Range: 4.0655. Min Range: -4.0655

Max Act: 3.9674. Min Act: -0.1700

Data Index: 1654596 (Open Web Text)

Max Activating Token Index: 601

Text #14

Max Range: 4.0655. Min Range: -4.0655

Max Act: 3.9477. Min Act: -0.1700

Data Index: 6839661 (Open Web Text)

Max Activating Token Index: 160

Text #15

Max Range: 4.0655. Min Range: -4.0655

Max Act: 3.9589. Min Act: -0.1700

Data Index: 6211759 (Open Web Text)

Max Activating Token Index: 826

Text #16

Max Range: 4.0655. Min Range: -4.0655

Max Act: 3.9490. Min Act: -0.1700

Data Index: 2889365 (Open Web Text)

Max Activating Token Index: 251

Text #17

Max Range: 4.0655. Min Range: -4.0655

Max Act: 3.9442. Min Act: -0.1700

Data Index: 1847950 (Open Web Text)

Max Activating Token Index: 844

Text #18

Max Range: 4.0655. Min Range: -4.0655

Max Act: 3.9471. Min Act: -0.1700

Data Index: 2783978 (Open Web Text)

Max Activating Token Index: 177

Text #19

Max Range: 4.0655. Min Range: -4.0655

Max Act: 3.9631. Min Act: -0.1700

Data Index: 4263165 (Open Web Text)

Max Activating Token Index: 818