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

Dataset: Open Web Text

Neuron 2390 in Layer 2

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: 2.1642. Min Range: -2.1642

Max Act: 2.1642. Min Act: -0.1700

Data Index: 8463657 (Open Web Text)

Max Activating Token Index: 643

Text #1

Max Range: 2.1642. Min Range: -2.1642

Max Act: 2.1236. Min Act: -0.1700

Data Index: 4417943 (Open Web Text)

Max Activating Token Index: 639

Text #2

Max Range: 2.1642. Min Range: -2.1642

Max Act: 2.0677. Min Act: -0.1700

Data Index: 5242125 (Open Web Text)

Max Activating Token Index: 493

Text #3

Max Range: 2.1642. Min Range: -2.1642

Max Act: 2.0815. Min Act: -0.1700

Data Index: 6551717 (Open Web Text)

Max Activating Token Index: 982

Text #4

Max Range: 2.1642. Min Range: -2.1642

Max Act: 2.0692. Min Act: -0.1700

Data Index: 4985219 (Open Web Text)

Max Activating Token Index: 116

Text #5

Max Range: 2.1642. Min Range: -2.1642

Max Act: 2.0355. Min Act: -0.1700

Data Index: 8639813 (Open Web Text)

Max Activating Token Index: 804

Text #6

Max Range: 2.1642. Min Range: -2.1642

Max Act: 2.0320. Min Act: -0.1700

Data Index: 6808815 (Open Web Text)

Max Activating Token Index: 198

Text #7

Max Range: 2.1642. Min Range: -2.1642

Max Act: 2.0182. Min Act: -0.1700

Data Index: 3377543 (Open Web Text)

Max Activating Token Index: 460

Text #8

Max Range: 2.1642. Min Range: -2.1642

Max Act: 2.0381. Min Act: -0.1700

Data Index: 4554446 (Open Web Text)

Max Activating Token Index: 231

Text #9

Max Range: 2.1642. Min Range: -2.1642

Max Act: 2.0149. Min Act: -0.1700

Data Index: 8298366 (Open Web Text)

Max Activating Token Index: 750

Text #10

Max Range: 2.1642. Min Range: -2.1642

Max Act: 2.0161. Min Act: -0.1700

Data Index: 5340814 (Open Web Text)

Max Activating Token Index: 815

Text #11

Max Range: 2.1642. Min Range: -2.1642

Max Act: 2.0285. Min Act: -0.1700

Data Index: 7008145 (Open Web Text)

Max Activating Token Index: 189

Text #12

Max Range: 2.1642. Min Range: -2.1642

Max Act: 2.0208. Min Act: -0.1700

Data Index: 6448369 (Open Web Text)

Max Activating Token Index: 487

Text #13

Max Range: 2.1642. Min Range: -2.1642

Max Act: 2.0271. Min Act: -0.1676

Data Index: 1579159 (Open Web Text)

Max Activating Token Index: 605

Text #14

Max Range: 2.1642. Min Range: -2.1642

Max Act: 2.0275. Min Act: -0.1700

Data Index: 2194711 (Open Web Text)

Max Activating Token Index: 13

Text #15

Max Range: 2.1642. Min Range: -2.1642

Max Act: 2.0018. Min Act: -0.1700

Data Index: 4642578 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 2.1642. Min Range: -2.1642

Max Act: 2.0166. Min Act: -0.1700

Data Index: 4127905 (Open Web Text)

Max Activating Token Index: 947

Text #17

Max Range: 2.1642. Min Range: -2.1642

Max Act: 1.9801. Min Act: -0.1700

Data Index: 2981760 (Open Web Text)

Max Activating Token Index: 436

Text #18

Max Range: 2.1642. Min Range: -2.1642

Max Act: 1.9932. Min Act: -0.1700

Data Index: 7358539 (Open Web Text)

Max Activating Token Index: 591

Text #19

Max Range: 2.1642. Min Range: -2.1642

Max Act: 1.9902. Min Act: -0.1700

Data Index: 4695564 (Open Web Text)

Max Activating Token Index: 11