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

Dataset: Open Web Text

Neuron 146 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: 3.6090. Min Range: -3.6090

Max Act: 3.6090. Min Act: -0.1700

Data Index: 7136202 (Open Web Text)

Max Activating Token Index: 954

Text #1

Max Range: 3.6090. Min Range: -3.6090

Max Act: 3.3127. Min Act: -0.1700

Data Index: 2409921 (Open Web Text)

Max Activating Token Index: 334

Text #2

Max Range: 3.6090. Min Range: -3.6090

Max Act: 3.2926. Min Act: -0.1700

Data Index: 40892 (Open Web Text)

Max Activating Token Index: 438

Text #3

Max Range: 3.6090. Min Range: -3.6090

Max Act: 3.2717. Min Act: -0.1700

Data Index: 848941 (Open Web Text)

Max Activating Token Index: 278

Text #4

Max Range: 3.6090. Min Range: -3.6090

Max Act: 3.2739. Min Act: -0.1700

Data Index: 6805860 (Open Web Text)

Max Activating Token Index: 706

Text #5

Max Range: 3.6090. Min Range: -3.6090

Max Act: 3.2387. Min Act: -0.1700

Data Index: 6217178 (Open Web Text)

Max Activating Token Index: 175

Text #6

Max Range: 3.6090. Min Range: -3.6090

Max Act: 3.2298. Min Act: -0.1700

Data Index: 3330645 (Open Web Text)

Max Activating Token Index: 373

Text #7

Max Range: 3.6090. Min Range: -3.6090

Max Act: 3.2195. Min Act: -0.1700

Data Index: 7760236 (Open Web Text)

Max Activating Token Index: 397

Text #8

Max Range: 3.6090. Min Range: -3.6090

Max Act: 3.1877. Min Act: -0.1700

Data Index: 7147212 (Open Web Text)

Max Activating Token Index: 726

Text #9

Max Range: 3.6090. Min Range: -3.6090

Max Act: 3.2061. Min Act: -0.1700

Data Index: 5417114 (Open Web Text)

Max Activating Token Index: 773

Text #10

Max Range: 3.6090. Min Range: -3.6090

Max Act: 3.1772. Min Act: -0.1700

Data Index: 6774411 (Open Web Text)

Max Activating Token Index: 291

Text #11

Max Range: 3.6090. Min Range: -3.6090

Max Act: 3.1618. Min Act: -0.1700

Data Index: 6669315 (Open Web Text)

Max Activating Token Index: 940

Text #12

Max Range: 3.6090. Min Range: -3.6090

Max Act: 3.1445. Min Act: -0.1700

Data Index: 8763210 (Open Web Text)

Max Activating Token Index: 84

Text #13

Max Range: 3.6090. Min Range: -3.6090

Max Act: 3.1091. Min Act: -0.1700

Data Index: 7883749 (Open Web Text)

Max Activating Token Index: 313

Text #14

Max Range: 3.6090. Min Range: -3.6090

Max Act: 3.0884. Min Act: -0.1700

Data Index: 4229179 (Open Web Text)

Max Activating Token Index: 593

Text #15

Max Range: 3.6090. Min Range: -3.6090

Max Act: 3.0986. Min Act: -0.1700

Data Index: 4044373 (Open Web Text)

Max Activating Token Index: 43

Text #16

Max Range: 3.6090. Min Range: -3.6090

Max Act: 3.1009. Min Act: -0.1700

Data Index: 5361288 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.6090. Min Range: -3.6090

Max Act: 3.0825. Min Act: -0.1700

Data Index: 2117965 (Open Web Text)

Max Activating Token Index: 654

Text #18

Max Range: 3.6090. Min Range: -3.6090

Max Act: 3.0855. Min Act: -0.1700

Data Index: 2644585 (Open Web Text)

Max Activating Token Index: 853

Text #19

Max Range: 3.6090. Min Range: -3.6090

Max Act: 3.0745. Min Act: -0.1700

Data Index: 6717285 (Open Web Text)

Max Activating Token Index: 652