Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer

Dataset: Open Web Text

Neuron 3352 in Layer 17

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')

Text #0

Max Range: 5.6771. Min Range: -5.6771

Max Act: 5.6771. Min Act: -0.1700

Data Index: 7369973 (Open Web Text)

Max Activating Token Index: 984

Text #1

Max Range: 5.6771. Min Range: -5.6771

Max Act: 5.6146. Min Act: -0.1700

Data Index: 1834698 (Open Web Text)

Max Activating Token Index: 648

Text #2

Max Range: 5.6771. Min Range: -5.6771

Max Act: 5.5521. Min Act: -0.1700

Data Index: 6093168 (Open Web Text)

Max Activating Token Index: 794

Text #3

Max Range: 5.6771. Min Range: -5.6771

Max Act: 5.5209. Min Act: -0.1700

Data Index: 8704604 (Open Web Text)

Max Activating Token Index: 254

Text #4

Max Range: 5.6771. Min Range: -5.6771

Max Act: 5.4896. Min Act: -0.1700

Data Index: 4035175 (Open Web Text)

Max Activating Token Index: 721

Text #5

Max Range: 5.6771. Min Range: -5.6771

Max Act: 5.5209. Min Act: -0.1700

Data Index: 7195066 (Open Web Text)

Max Activating Token Index: 172

Text #6

Max Range: 5.6771. Min Range: -5.6771

Max Act: 5.5209. Min Act: -0.1700

Data Index: 5962119 (Open Web Text)

Max Activating Token Index: 503

Text #7

Max Range: 5.6771. Min Range: -5.6771

Max Act: 5.5209. Min Act: -0.1700

Data Index: 2250915 (Open Web Text)

Max Activating Token Index: 532

Text #8

Max Range: 5.6771. Min Range: -5.6771

Max Act: 5.4584. Min Act: -0.1700

Data Index: 3044343 (Open Web Text)

Max Activating Token Index: 576

Text #9

Max Range: 5.6771. Min Range: -5.6771

Max Act: 5.4896. Min Act: -0.1700

Data Index: 2550320 (Open Web Text)

Max Activating Token Index: 523

Text #10

Max Range: 5.6771. Min Range: -5.6771

Max Act: 5.4896. Min Act: -0.1700

Data Index: 1154160 (Open Web Text)

Max Activating Token Index: 479

Text #11

Max Range: 5.6771. Min Range: -5.6771

Max Act: 5.4896. Min Act: -0.1700

Data Index: 3651225 (Open Web Text)

Max Activating Token Index: 909

Text #12

Max Range: 5.6771. Min Range: -5.6771

Max Act: 5.4584. Min Act: -0.1700

Data Index: 7942773 (Open Web Text)

Max Activating Token Index: 293

Text #13

Max Range: 5.6771. Min Range: -5.6771

Max Act: 5.4584. Min Act: -0.1700

Data Index: 2415359 (Open Web Text)

Max Activating Token Index: 569

Text #14

Max Range: 5.6771. Min Range: -5.6771

Max Act: 5.4271. Min Act: -0.1700

Data Index: 8738813 (Open Web Text)

Max Activating Token Index: 271

Text #15

Max Range: 5.6771. Min Range: -5.6771

Max Act: 5.3959. Min Act: -0.1700

Data Index: 6199742 (Open Web Text)

Max Activating Token Index: 980

Text #16

Max Range: 5.6771. Min Range: -5.6771

Max Act: 5.3959. Min Act: -0.1700

Data Index: 2131071 (Open Web Text)

Max Activating Token Index: 764

Text #17

Max Range: 5.6771. Min Range: -5.6771

Max Act: 5.3334. Min Act: -0.1700

Data Index: 5414093 (Open Web Text)

Max Activating Token Index: 321

Text #18

Max Range: 5.6771. Min Range: -5.6771

Max Act: 5.3959. Min Act: -0.1700

Data Index: 7717354 (Open Web Text)

Max Activating Token Index: 228

Text #19

Max Range: 5.6771. Min Range: -5.6771

Max Act: 5.3646. Min Act: -0.1700

Data Index: 5253127 (Open Web Text)

Max Activating Token Index: 194