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

Dataset: Open Web Text

Neuron 2216 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: 4.6479. Min Range: -4.6479

Max Act: 4.6479. Min Act: -0.1700

Data Index: 6274516 (Open Web Text)

Max Activating Token Index: 439

Text #1

Max Range: 4.6479. Min Range: -4.6479

Max Act: 4.6407. Min Act: -0.1700

Data Index: 2662511 (Open Web Text)

Max Activating Token Index: 97

Text #2

Max Range: 4.6479. Min Range: -4.6479

Max Act: 4.6078. Min Act: -0.1700

Data Index: 4375015 (Open Web Text)

Max Activating Token Index: 220

Text #3

Max Range: 4.6479. Min Range: -4.6479

Max Act: 4.5688. Min Act: -0.1700

Data Index: 4645488 (Open Web Text)

Max Activating Token Index: 951

Text #4

Max Range: 4.6479. Min Range: -4.6479

Max Act: 4.5885. Min Act: -0.1700

Data Index: 1251104 (Open Web Text)

Max Activating Token Index: 256

Text #5

Max Range: 4.6479. Min Range: -4.6479

Max Act: 4.5614. Min Act: -0.1700

Data Index: 802578 (Open Web Text)

Max Activating Token Index: 1004

Text #6

Max Range: 4.6479. Min Range: -4.6479

Max Act: 4.5142. Min Act: -0.1700

Data Index: 2037839 (Open Web Text)

Max Activating Token Index: 338

Text #7

Max Range: 4.6479. Min Range: -4.6479

Max Act: 4.5344. Min Act: -0.1700

Data Index: 8768746 (Open Web Text)

Max Activating Token Index: 923

Text #8

Max Range: 4.6479. Min Range: -4.6479

Max Act: 4.5572. Min Act: -0.1700

Data Index: 1344199 (Open Web Text)

Max Activating Token Index: 652

Text #9

Max Range: 4.6479. Min Range: -4.6479

Max Act: 4.5297. Min Act: -0.1700

Data Index: 5008427 (Open Web Text)

Max Activating Token Index: 98

Text #10

Max Range: 4.6479. Min Range: -4.6479

Max Act: 4.5240. Min Act: -0.1700

Data Index: 3274744 (Open Web Text)

Max Activating Token Index: 600

Text #11

Max Range: 4.6479. Min Range: -4.6479

Max Act: 4.4812. Min Act: -0.1700

Data Index: 8197933 (Open Web Text)

Max Activating Token Index: 49

Text #12

Max Range: 4.6479. Min Range: -4.6479

Max Act: 4.5019. Min Act: -0.1700

Data Index: 2296301 (Open Web Text)

Max Activating Token Index: 761

Text #13

Max Range: 4.6479. Min Range: -4.6479

Max Act: 4.5036. Min Act: -0.1700

Data Index: 6981206 (Open Web Text)

Max Activating Token Index: 939

Text #14

Max Range: 4.6479. Min Range: -4.6479

Max Act: 4.5008. Min Act: -0.1700

Data Index: 2868295 (Open Web Text)

Max Activating Token Index: 821

Text #15

Max Range: 4.6479. Min Range: -4.6479

Max Act: 4.4392. Min Act: -0.1700

Data Index: 602884 (Open Web Text)

Max Activating Token Index: 635

Text #16

Max Range: 4.6479. Min Range: -4.6479

Max Act: 4.4648. Min Act: -0.1700

Data Index: 6696256 (Open Web Text)

Max Activating Token Index: 327

Text #17

Max Range: 4.6479. Min Range: -4.6479

Max Act: 4.4668. Min Act: -0.1700

Data Index: 564430 (Open Web Text)

Max Activating Token Index: 589

Text #18

Max Range: 4.6479. Min Range: -4.6479

Max Act: 4.4522. Min Act: -0.1700

Data Index: 4710476 (Open Web Text)

Max Activating Token Index: 399

Text #19

Max Range: 4.6479. Min Range: -4.6479

Max Act: 4.4256. Min Act: -0.1700

Data Index: 3055725 (Open Web Text)

Max Activating Token Index: 504