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

Dataset: Open Web Text

Neuron 1026 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: 5.1701. Min Range: -5.1701

Max Act: 5.1701. Min Act: -0.1700

Data Index: 5718582 (Open Web Text)

Max Activating Token Index: 559

Text #1

Max Range: 5.1701. Min Range: -5.1701

Max Act: 5.0989. Min Act: -0.1700

Data Index: 4595564 (Open Web Text)

Max Activating Token Index: 90

Text #2

Max Range: 5.1701. Min Range: -5.1701

Max Act: 5.0400. Min Act: -0.1700

Data Index: 2131994 (Open Web Text)

Max Activating Token Index: 620

Text #3

Max Range: 5.1701. Min Range: -5.1701

Max Act: 4.9428. Min Act: -0.1700

Data Index: 4189332 (Open Web Text)

Max Activating Token Index: 994

Text #4

Max Range: 5.1701. Min Range: -5.1701

Max Act: 4.9015. Min Act: -0.1700

Data Index: 5691372 (Open Web Text)

Max Activating Token Index: 361

Text #5

Max Range: 5.1701. Min Range: -5.1701

Max Act: 4.8692. Min Act: -0.1700

Data Index: 1766013 (Open Web Text)

Max Activating Token Index: 348

Text #6

Max Range: 5.1701. Min Range: -5.1701

Max Act: 4.8568. Min Act: -0.1700

Data Index: 7955589 (Open Web Text)

Max Activating Token Index: 690

Text #7

Max Range: 5.1701. Min Range: -5.1701

Max Act: 4.8651. Min Act: -0.1700

Data Index: 4060404 (Open Web Text)

Max Activating Token Index: 80

Text #8

Max Range: 5.1701. Min Range: -5.1701

Max Act: 4.8281. Min Act: -0.1700

Data Index: 6358104 (Open Web Text)

Max Activating Token Index: 450

Text #9

Max Range: 5.1701. Min Range: -5.1701

Max Act: 4.8098. Min Act: -0.1700

Data Index: 5062391 (Open Web Text)

Max Activating Token Index: 807

Text #10

Max Range: 5.1701. Min Range: -5.1701

Max Act: 4.8030. Min Act: -0.1700

Data Index: 5456656 (Open Web Text)

Max Activating Token Index: 305

Text #11

Max Range: 5.1701. Min Range: -5.1701

Max Act: 4.7863. Min Act: -0.1700

Data Index: 4326504 (Open Web Text)

Max Activating Token Index: 233

Text #12

Max Range: 5.1701. Min Range: -5.1701

Max Act: 4.7548. Min Act: -0.1700

Data Index: 7449426 (Open Web Text)

Max Activating Token Index: 78

Text #13

Max Range: 5.1701. Min Range: -5.1701

Max Act: 4.7555. Min Act: -0.1700

Data Index: 3999429 (Open Web Text)

Max Activating Token Index: 235

Text #14

Max Range: 5.1701. Min Range: -5.1701

Max Act: 4.7790. Min Act: -0.1700

Data Index: 3940011 (Open Web Text)

Max Activating Token Index: 300

Text #15

Max Range: 5.1701. Min Range: -5.1701

Max Act: 4.7946. Min Act: -0.1700

Data Index: 655501 (Open Web Text)

Max Activating Token Index: 982

Text #16

Max Range: 5.1701. Min Range: -5.1701

Max Act: 4.7980. Min Act: -0.1700

Data Index: 3901393 (Open Web Text)

Max Activating Token Index: 297

Text #17

Max Range: 5.1701. Min Range: -5.1701

Max Act: 4.7343. Min Act: -0.1700

Data Index: 834658 (Open Web Text)

Max Activating Token Index: 137

Text #18

Max Range: 5.1701. Min Range: -5.1701

Max Act: 4.7498. Min Act: -0.1700

Data Index: 2765981 (Open Web Text)

Max Activating Token Index: 104

Text #19

Max Range: 5.1701. Min Range: -5.1701

Max Act: 4.7453. Min Act: -0.1700

Data Index: 4131093 (Open Web Text)

Max Activating Token Index: 102