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

Dataset: Open Web Text

Neuron 1704 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: 3.1055. Min Range: -3.1055

Max Act: 3.0888. Min Act: -0.1700

Data Index: 2910659 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.1055. Min Range: -3.1055

Max Act: 3.1055. Min Act: -0.1700

Data Index: 4781555 (Open Web Text)

Max Activating Token Index: 324

Text #2

Max Range: 3.1055. Min Range: -3.1055

Max Act: 3.0641. Min Act: -0.1700

Data Index: 3617646 (Open Web Text)

Max Activating Token Index: 1019

Text #3

Max Range: 3.1055. Min Range: -3.1055

Max Act: 3.0719. Min Act: -0.1700

Data Index: 2234221 (Open Web Text)

Max Activating Token Index: 240

Text #4

Max Range: 3.1055. Min Range: -3.1055

Max Act: 3.0795. Min Act: -0.1700

Data Index: 8225119 (Open Web Text)

Max Activating Token Index: 678

Text #5

Max Range: 3.1055. Min Range: -3.1055

Max Act: 3.0517. Min Act: -0.1700

Data Index: 1239547 (Open Web Text)

Max Activating Token Index: 1013

Text #6

Max Range: 3.1055. Min Range: -3.1055

Max Act: 3.0478. Min Act: -0.1700

Data Index: 5775918 (Open Web Text)

Max Activating Token Index: 667

Text #7

Max Range: 3.1055. Min Range: -3.1055

Max Act: 3.0146. Min Act: -0.1700

Data Index: 2931216 (Open Web Text)

Max Activating Token Index: 998

Text #8

Max Range: 3.1055. Min Range: -3.1055

Max Act: 3.0167. Min Act: -0.1700

Data Index: 5124345 (Open Web Text)

Max Activating Token Index: 264

Text #9

Max Range: 3.1055. Min Range: -3.1055

Max Act: 3.0029. Min Act: -0.1700

Data Index: 7952173 (Open Web Text)

Max Activating Token Index: 163

Text #10

Max Range: 3.1055. Min Range: -3.1055

Max Act: 3.0199. Min Act: -0.1700

Data Index: 2868938 (Open Web Text)

Max Activating Token Index: 795

Text #11

Max Range: 3.1055. Min Range: -3.1055

Max Act: 3.0298. Min Act: -0.1700

Data Index: 1382333 (Open Web Text)

Max Activating Token Index: 847

Text #12

Max Range: 3.1055. Min Range: -3.1055

Max Act: 2.9767. Min Act: -0.1700

Data Index: 7514424 (Open Web Text)

Max Activating Token Index: 157

Text #13

Max Range: 3.1055. Min Range: -3.1055

Max Act: 2.9955. Min Act: -0.1700

Data Index: 5263430 (Open Web Text)

Max Activating Token Index: 1018

Text #14

Max Range: 3.1055. Min Range: -3.1055

Max Act: 2.9996. Min Act: -0.1700

Data Index: 8764911 (Open Web Text)

Max Activating Token Index: 621

Text #15

Max Range: 3.1055. Min Range: -3.1055

Max Act: 3.0031. Min Act: -0.1700

Data Index: 5180510 (Open Web Text)

Max Activating Token Index: 385

Text #16

Max Range: 3.1055. Min Range: -3.1055

Max Act: 2.9622. Min Act: -0.1700

Data Index: 7342061 (Open Web Text)

Max Activating Token Index: 782

Text #17

Max Range: 3.1055. Min Range: -3.1055

Max Act: 2.9846. Min Act: -0.1700

Data Index: 7768153 (Open Web Text)

Max Activating Token Index: 282

Text #18

Max Range: 3.1055. Min Range: -3.1055

Max Act: 2.9754. Min Act: -0.1700

Data Index: 5476573 (Open Web Text)

Max Activating Token Index: 54

Text #19

Max Range: 3.1055. Min Range: -3.1055

Max Act: 2.9634. Min Act: -0.1700

Data Index: 5552353 (Open Web Text)

Max Activating Token Index: 17