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

Dataset: Open Web Text

Neuron 1278 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: 6.6871. Min Range: -6.6871

Max Act: 6.6871. Min Act: -0.1700

Data Index: 3374824 (Open Web Text)

Max Activating Token Index: 575

Text #1

Max Range: 6.6871. Min Range: -6.6871

Max Act: 6.6454. Min Act: -0.1700

Data Index: 3568918 (Open Web Text)

Max Activating Token Index: 873

Text #2

Max Range: 6.6871. Min Range: -6.6871

Max Act: 6.6655. Min Act: -0.1700

Data Index: 6619106 (Open Web Text)

Max Activating Token Index: 986

Text #3

Max Range: 6.6871. Min Range: -6.6871

Max Act: 6.5099. Min Act: -0.1700

Data Index: 865582 (Open Web Text)

Max Activating Token Index: 356

Text #4

Max Range: 6.6871. Min Range: -6.6871

Max Act: 6.4351. Min Act: -0.1700

Data Index: 6073036 (Open Web Text)

Max Activating Token Index: 500

Text #5

Max Range: 6.6871. Min Range: -6.6871

Max Act: 6.4496. Min Act: -0.1700

Data Index: 5577709 (Open Web Text)

Max Activating Token Index: 889

Text #6

Max Range: 6.6871. Min Range: -6.6871

Max Act: 6.4062. Min Act: -0.1700

Data Index: 195190 (Open Web Text)

Max Activating Token Index: 382

Text #7

Max Range: 6.6871. Min Range: -6.6871

Max Act: 6.3382. Min Act: -0.1700

Data Index: 3599020 (Open Web Text)

Max Activating Token Index: 247

Text #8

Max Range: 6.6871. Min Range: -6.6871

Max Act: 6.3651. Min Act: -0.1700

Data Index: 4358797 (Open Web Text)

Max Activating Token Index: 251

Text #9

Max Range: 6.6871. Min Range: -6.6871

Max Act: 6.3623. Min Act: -0.1700

Data Index: 6738933 (Open Web Text)

Max Activating Token Index: 471

Text #10

Max Range: 6.6871. Min Range: -6.6871

Max Act: 6.3361. Min Act: -0.1700

Data Index: 4976437 (Open Web Text)

Max Activating Token Index: 23

Text #11

Max Range: 6.6871. Min Range: -6.6871

Max Act: 6.3564. Min Act: -0.1700

Data Index: 8322840 (Open Web Text)

Max Activating Token Index: 777

Text #12

Max Range: 6.6871. Min Range: -6.6871

Max Act: 6.2589. Min Act: -0.1700

Data Index: 1352426 (Open Web Text)

Max Activating Token Index: 651

Text #13

Max Range: 6.6871. Min Range: -6.6871

Max Act: 6.3637. Min Act: -0.1700

Data Index: 4710280 (Open Web Text)

Max Activating Token Index: 377

Text #14

Max Range: 6.6871. Min Range: -6.6871

Max Act: 6.3158. Min Act: -0.1700

Data Index: 6374616 (Open Web Text)

Max Activating Token Index: 348

Text #15

Max Range: 6.6871. Min Range: -6.6871

Max Act: 6.3332. Min Act: -0.1700

Data Index: 5920854 (Open Web Text)

Max Activating Token Index: 323

Text #16

Max Range: 6.6871. Min Range: -6.6871

Max Act: 6.2558. Min Act: -0.1700

Data Index: 5630335 (Open Web Text)

Max Activating Token Index: 340

Text #17

Max Range: 6.6871. Min Range: -6.6871

Max Act: 6.3846. Min Act: -0.1700

Data Index: 5375397 (Open Web Text)

Max Activating Token Index: 770

Text #18

Max Range: 6.6871. Min Range: -6.6871

Max Act: 6.2851. Min Act: -0.1700

Data Index: 6373850 (Open Web Text)

Max Activating Token Index: 270

Text #19

Max Range: 6.6871. Min Range: -6.6871

Max Act: 6.2843. Min Act: -0.1700

Data Index: 5309418 (Open Web Text)

Max Activating Token Index: 387