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

Dataset: Open Web Text

Neuron 1824 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: 4.9838. Min Range: -4.9838

Max Act: 4.9838. Min Act: -0.1700

Data Index: 6333587 (Open Web Text)

Max Activating Token Index: 128

Text #1

Max Range: 4.9838. Min Range: -4.9838

Max Act: 4.9173. Min Act: -0.1700

Data Index: 6134358 (Open Web Text)

Max Activating Token Index: 29

Text #2

Max Range: 4.9838. Min Range: -4.9838

Max Act: 4.8713. Min Act: -0.1700

Data Index: 289957 (Open Web Text)

Max Activating Token Index: 285

Text #3

Max Range: 4.9838. Min Range: -4.9838

Max Act: 4.8284. Min Act: -0.1700

Data Index: 3567838 (Open Web Text)

Max Activating Token Index: 737

Text #4

Max Range: 4.9838. Min Range: -4.9838

Max Act: 4.8190. Min Act: -0.1700

Data Index: 4608349 (Open Web Text)

Max Activating Token Index: 701

Text #5

Max Range: 4.9838. Min Range: -4.9838

Max Act: 4.8371. Min Act: -0.1700

Data Index: 236020 (Open Web Text)

Max Activating Token Index: 212

Text #6

Max Range: 4.9838. Min Range: -4.9838

Max Act: 4.8324. Min Act: -0.1700

Data Index: 1028979 (Open Web Text)

Max Activating Token Index: 767

Text #7

Max Range: 4.9838. Min Range: -4.9838

Max Act: 4.7842. Min Act: -0.1700

Data Index: 5039491 (Open Web Text)

Max Activating Token Index: 31

Text #8

Max Range: 4.9838. Min Range: -4.9838

Max Act: 4.7650. Min Act: -0.1700

Data Index: 5423828 (Open Web Text)

Max Activating Token Index: 535

Text #9

Max Range: 4.9838. Min Range: -4.9838

Max Act: 4.7330. Min Act: -0.1700

Data Index: 6978341 (Open Web Text)

Max Activating Token Index: 362

Text #10

Max Range: 4.9838. Min Range: -4.9838

Max Act: 4.6969. Min Act: -0.1700

Data Index: 2944864 (Open Web Text)

Max Activating Token Index: 646

Text #11

Max Range: 4.9838. Min Range: -4.9838

Max Act: 4.7212. Min Act: -0.1700

Data Index: 5896555 (Open Web Text)

Max Activating Token Index: 180

Text #12

Max Range: 4.9838. Min Range: -4.9838

Max Act: 4.6815. Min Act: -0.1700

Data Index: 2054853 (Open Web Text)

Max Activating Token Index: 382

Text #13

Max Range: 4.9838. Min Range: -4.9838

Max Act: 4.7052. Min Act: -0.1700

Data Index: 1480503 (Open Web Text)

Max Activating Token Index: 538

Text #14

Max Range: 4.9838. Min Range: -4.9838

Max Act: 4.7152. Min Act: -0.1700

Data Index: 846815 (Open Web Text)

Max Activating Token Index: 846

Text #15

Max Range: 4.9838. Min Range: -4.9838

Max Act: 4.6866. Min Act: -0.1700

Data Index: 2647595 (Open Web Text)

Max Activating Token Index: 657

Text #16

Max Range: 4.9838. Min Range: -4.9838

Max Act: 4.6608. Min Act: -0.1700

Data Index: 6259009 (Open Web Text)

Max Activating Token Index: 377

Text #17

Max Range: 4.9838. Min Range: -4.9838

Max Act: 4.6980. Min Act: -0.1700

Data Index: 1133434 (Open Web Text)

Max Activating Token Index: 325

Text #18

Max Range: 4.9838. Min Range: -4.9838

Max Act: 4.6643. Min Act: -0.1700

Data Index: 4033467 (Open Web Text)

Max Activating Token Index: 828

Text #19

Max Range: 4.9838. Min Range: -4.9838

Max Act: 4.7017. Min Act: -0.1700

Data Index: 3230115 (Open Web Text)

Max Activating Token Index: 168