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

Dataset: Open Web Text

Neuron 746 in Layer 5

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: 6.1704. Min Range: -6.1704

Max Act: 6.1704. Min Act: -0.1700

Data Index: 7482624 (Open Web Text)

Max Activating Token Index: 128

Text #1

Max Range: 6.1704. Min Range: -6.1704

Max Act: 6.0236. Min Act: -0.1700

Data Index: 5338476 (Open Web Text)

Max Activating Token Index: 395

Text #2

Max Range: 6.1704. Min Range: -6.1704

Max Act: 6.1210. Min Act: -0.1700

Data Index: 860346 (Open Web Text)

Max Activating Token Index: 229

Text #3

Max Range: 6.1704. Min Range: -6.1704

Max Act: 5.9694. Min Act: -0.1700

Data Index: 7767276 (Open Web Text)

Max Activating Token Index: 939

Text #4

Max Range: 6.1704. Min Range: -6.1704

Max Act: 5.8749. Min Act: -0.1700

Data Index: 7687027 (Open Web Text)

Max Activating Token Index: 461

Text #5

Max Range: 6.1704. Min Range: -6.1704

Max Act: 5.9767. Min Act: -0.1700

Data Index: 2058874 (Open Web Text)

Max Activating Token Index: 280

Text #6

Max Range: 6.1704. Min Range: -6.1704

Max Act: 5.9425. Min Act: -0.1700

Data Index: 8197518 (Open Web Text)

Max Activating Token Index: 672

Text #7

Max Range: 6.1704. Min Range: -6.1704

Max Act: 5.9704. Min Act: -0.1700

Data Index: 6912108 (Open Web Text)

Max Activating Token Index: 760

Text #8

Max Range: 6.1704. Min Range: -6.1704

Max Act: 5.8809. Min Act: -0.1700

Data Index: 7878549 (Open Web Text)

Max Activating Token Index: 793

Text #9

Max Range: 6.1704. Min Range: -6.1704

Max Act: 5.9114. Min Act: -0.1700

Data Index: 1513408 (Open Web Text)

Max Activating Token Index: 111

Text #10

Max Range: 6.1704. Min Range: -6.1704

Max Act: 5.8713. Min Act: -0.1700

Data Index: 5383090 (Open Web Text)

Max Activating Token Index: 27

Text #11

Max Range: 6.1704. Min Range: -6.1704

Max Act: 5.9128. Min Act: -0.1700

Data Index: 4293130 (Open Web Text)

Max Activating Token Index: 185

Text #12

Max Range: 6.1704. Min Range: -6.1704

Max Act: 5.8385. Min Act: -0.1700

Data Index: 6018507 (Open Web Text)

Max Activating Token Index: 382

Text #13

Max Range: 6.1704. Min Range: -6.1704

Max Act: 5.8386. Min Act: -0.1700

Data Index: 5286458 (Open Web Text)

Max Activating Token Index: 941

Text #14

Max Range: 6.1704. Min Range: -6.1704

Max Act: 5.8471. Min Act: -0.1700

Data Index: 8213148 (Open Web Text)

Max Activating Token Index: 536

Text #15

Max Range: 6.1704. Min Range: -6.1704

Max Act: 5.9197. Min Act: -0.1700

Data Index: 1651629 (Open Web Text)

Max Activating Token Index: 820

Text #16

Max Range: 6.1704. Min Range: -6.1704

Max Act: 5.8340. Min Act: -0.1700

Data Index: 1154923 (Open Web Text)

Max Activating Token Index: 347

Text #17

Max Range: 6.1704. Min Range: -6.1704

Max Act: 5.7582. Min Act: -0.1700

Data Index: 5157504 (Open Web Text)

Max Activating Token Index: 671

Text #18

Max Range: 6.1704. Min Range: -6.1704

Max Act: 5.8451. Min Act: -0.1700

Data Index: 3684525 (Open Web Text)

Max Activating Token Index: 670

Text #19

Max Range: 6.1704. Min Range: -6.1704

Max Act: 5.7839. Min Act: -0.1700

Data Index: 216035 (Open Web Text)

Max Activating Token Index: 572