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

Dataset: Open Web Text

Neuron 2849 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: 4.7546. Min Range: -4.7546

Max Act: 4.7546. Min Act: -0.1700

Data Index: 4550187 (Open Web Text)

Max Activating Token Index: 48

Text #1

Max Range: 4.7546. Min Range: -4.7546

Max Act: 4.6574. Min Act: -0.1700

Data Index: 2210867 (Open Web Text)

Max Activating Token Index: 651

Text #2

Max Range: 4.7546. Min Range: -4.7546

Max Act: 4.6341. Min Act: -0.1700

Data Index: 6484952 (Open Web Text)

Max Activating Token Index: 528

Text #3

Max Range: 4.7546. Min Range: -4.7546

Max Act: 4.6171. Min Act: -0.1700

Data Index: 995594 (Open Web Text)

Max Activating Token Index: 344

Text #4

Max Range: 4.7546. Min Range: -4.7546

Max Act: 4.6392. Min Act: -0.1700

Data Index: 7983670 (Open Web Text)

Max Activating Token Index: 113

Text #5

Max Range: 4.7546. Min Range: -4.7546

Max Act: 4.6152. Min Act: -0.1700

Data Index: 2387179 (Open Web Text)

Max Activating Token Index: 210

Text #6

Max Range: 4.7546. Min Range: -4.7546

Max Act: 4.5809. Min Act: -0.1700

Data Index: 4754291 (Open Web Text)

Max Activating Token Index: 103

Text #7

Max Range: 4.7546. Min Range: -4.7546

Max Act: 4.5701. Min Act: -0.1700

Data Index: 2575824 (Open Web Text)

Max Activating Token Index: 46

Text #8

Max Range: 4.7546. Min Range: -4.7546

Max Act: 4.5782. Min Act: -0.1700

Data Index: 6848469 (Open Web Text)

Max Activating Token Index: 136

Text #9

Max Range: 4.7546. Min Range: -4.7546

Max Act: 4.5584. Min Act: -0.1700

Data Index: 4044706 (Open Web Text)

Max Activating Token Index: 240

Text #10

Max Range: 4.7546. Min Range: -4.7546

Max Act: 4.5180. Min Act: -0.1700

Data Index: 387903 (Open Web Text)

Max Activating Token Index: 534

Text #11

Max Range: 4.7546. Min Range: -4.7546

Max Act: 4.5348. Min Act: -0.1700

Data Index: 2706148 (Open Web Text)

Max Activating Token Index: 21

Text #12

Max Range: 4.7546. Min Range: -4.7546

Max Act: 4.5308. Min Act: -0.1700

Data Index: 3256981 (Open Web Text)

Max Activating Token Index: 727

Text #13

Max Range: 4.7546. Min Range: -4.7546

Max Act: 4.5155. Min Act: -0.1700

Data Index: 2851081 (Open Web Text)

Max Activating Token Index: 446

Text #14

Max Range: 4.7546. Min Range: -4.7546

Max Act: 4.5299. Min Act: -0.1700

Data Index: 2387181 (Open Web Text)

Max Activating Token Index: 32

Text #15

Max Range: 4.7546. Min Range: -4.7546

Max Act: 4.4897. Min Act: -0.1699

Data Index: 1787164 (Open Web Text)

Max Activating Token Index: 79

Text #16

Max Range: 4.7546. Min Range: -4.7546

Max Act: 4.4960. Min Act: -0.1700

Data Index: 2793799 (Open Web Text)

Max Activating Token Index: 264

Text #17

Max Range: 4.7546. Min Range: -4.7546

Max Act: 4.4921. Min Act: -0.1700

Data Index: 4739558 (Open Web Text)

Max Activating Token Index: 314

Text #18

Max Range: 4.7546. Min Range: -4.7546

Max Act: 4.4840. Min Act: -0.1700

Data Index: 4827400 (Open Web Text)

Max Activating Token Index: 496

Text #19

Max Range: 4.7546. Min Range: -4.7546

Max Act: 4.4938. Min Act: -0.1700

Data Index: 5076107 (Open Web Text)

Max Activating Token Index: 975