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

Dataset: Open Web Text

Neuron 3026 in Layer 1

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: 1.5793. Min Range: -1.5793

Max Act: 1.5793. Min Act: -0.1700

Data Index: 3738928 (Open Web Text)

Max Activating Token Index: 342

Text #1

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.5396. Min Act: -0.1700

Data Index: 2501665 (Open Web Text)

Max Activating Token Index: 129

Text #2

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.5374. Min Act: -0.1700

Data Index: 4728380 (Open Web Text)

Max Activating Token Index: 63

Text #3

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.5315. Min Act: -0.1697

Data Index: 1492922 (Open Web Text)

Max Activating Token Index: 597

Text #4

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.5204. Min Act: -0.1700

Data Index: 5810524 (Open Web Text)

Max Activating Token Index: 345

Text #5

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.5242. Min Act: -0.1700

Data Index: 4159096 (Open Web Text)

Max Activating Token Index: 606

Text #6

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.5141. Min Act: -0.1700

Data Index: 7418617 (Open Web Text)

Max Activating Token Index: 631

Text #7

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.5181. Min Act: -0.1700

Data Index: 5469939 (Open Web Text)

Max Activating Token Index: 446

Text #8

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.5181. Min Act: -0.1700

Data Index: 2169295 (Open Web Text)

Max Activating Token Index: 752

Text #9

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.5278. Min Act: -0.1700

Data Index: 166723 (Open Web Text)

Max Activating Token Index: 964

Text #10

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.5122. Min Act: -0.1700

Data Index: 8501581 (Open Web Text)

Max Activating Token Index: 160

Text #11

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.5007. Min Act: -0.1700

Data Index: 248510 (Open Web Text)

Max Activating Token Index: 909

Text #12

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.5019. Min Act: -0.1700

Data Index: 5595243 (Open Web Text)

Max Activating Token Index: 342

Text #13

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.5136. Min Act: -0.1700

Data Index: 6385389 (Open Web Text)

Max Activating Token Index: 149

Text #14

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.4972. Min Act: -0.1700

Data Index: 7863491 (Open Web Text)

Max Activating Token Index: 639

Text #15

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.5008. Min Act: -0.1700

Data Index: 5959648 (Open Web Text)

Max Activating Token Index: 471

Text #16

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.4957. Min Act: -0.1700

Data Index: 351410 (Open Web Text)

Max Activating Token Index: 517

Text #17

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.4835. Min Act: -0.1700

Data Index: 4168346 (Open Web Text)

Max Activating Token Index: 676

Text #18

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.4931. Min Act: -0.1700

Data Index: 1889001 (Open Web Text)

Max Activating Token Index: 112

Text #19

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.4948. Min Act: -0.1700

Data Index: 5189578 (Open Web Text)

Max Activating Token Index: 429