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

Dataset: Open Web Text

Neuron 2639 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: 4.8872. Min Range: -4.8872

Max Act: 4.8872. Min Act: -0.1700

Data Index: 4272719 (Open Web Text)

Max Activating Token Index: 565

Text #1

Max Range: 4.8872. Min Range: -4.8872

Max Act: 4.8254. Min Act: -0.1700

Data Index: 4923257 (Open Web Text)

Max Activating Token Index: 644

Text #2

Max Range: 4.8872. Min Range: -4.8872

Max Act: 4.8084. Min Act: -0.1700

Data Index: 5336070 (Open Web Text)

Max Activating Token Index: 379

Text #3

Max Range: 4.8872. Min Range: -4.8872

Max Act: 4.7977. Min Act: -0.1700

Data Index: 4682270 (Open Web Text)

Max Activating Token Index: 326

Text #4

Max Range: 4.8872. Min Range: -4.8872

Max Act: 4.8116. Min Act: -0.1700

Data Index: 1513140 (Open Web Text)

Max Activating Token Index: 497

Text #5

Max Range: 4.8872. Min Range: -4.8872

Max Act: 4.7776. Min Act: -0.1700

Data Index: 7628295 (Open Web Text)

Max Activating Token Index: 875

Text #6

Max Range: 4.8872. Min Range: -4.8872

Max Act: 4.7771. Min Act: -0.1700

Data Index: 927659 (Open Web Text)

Max Activating Token Index: 349

Text #7

Max Range: 4.8872. Min Range: -4.8872

Max Act: 4.7186. Min Act: -0.1700

Data Index: 4098161 (Open Web Text)

Max Activating Token Index: 759

Text #8

Max Range: 4.8872. Min Range: -4.8872

Max Act: 4.7306. Min Act: -0.1700

Data Index: 372719 (Open Web Text)

Max Activating Token Index: 212

Text #9

Max Range: 4.8872. Min Range: -4.8872

Max Act: 4.7018. Min Act: -0.1700

Data Index: 5005417 (Open Web Text)

Max Activating Token Index: 579

Text #10

Max Range: 4.8872. Min Range: -4.8872

Max Act: 4.7005. Min Act: -0.1700

Data Index: 4071702 (Open Web Text)

Max Activating Token Index: 177

Text #11

Max Range: 4.8872. Min Range: -4.8872

Max Act: 4.6833. Min Act: -0.1700

Data Index: 7423249 (Open Web Text)

Max Activating Token Index: 354

Text #12

Max Range: 4.8872. Min Range: -4.8872

Max Act: 4.6890. Min Act: -0.1700

Data Index: 6412115 (Open Web Text)

Max Activating Token Index: 716

Text #13

Max Range: 4.8872. Min Range: -4.8872

Max Act: 4.7029. Min Act: -0.1700

Data Index: 1994616 (Open Web Text)

Max Activating Token Index: 571

Text #14

Max Range: 4.8872. Min Range: -4.8872

Max Act: 4.6658. Min Act: -0.1700

Data Index: 6474899 (Open Web Text)

Max Activating Token Index: 653

Text #15

Max Range: 4.8872. Min Range: -4.8872

Max Act: 4.6683. Min Act: -0.1700

Data Index: 8759586 (Open Web Text)

Max Activating Token Index: 480

Text #16

Max Range: 4.8872. Min Range: -4.8872

Max Act: 4.6654. Min Act: -0.1700

Data Index: 7533992 (Open Web Text)

Max Activating Token Index: 678

Text #17

Max Range: 4.8872. Min Range: -4.8872

Max Act: 4.6296. Min Act: -0.1700

Data Index: 3551286 (Open Web Text)

Max Activating Token Index: 653

Text #18

Max Range: 4.8872. Min Range: -4.8872

Max Act: 4.6402. Min Act: -0.1700

Data Index: 4285742 (Open Web Text)

Max Activating Token Index: 73

Text #19

Max Range: 4.8872. Min Range: -4.8872

Max Act: 4.6361. Min Act: -0.1700

Data Index: 5324240 (Open Web Text)

Max Activating Token Index: 131