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

Dataset: Open Web Text

Neuron 576 in Layer 2

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: 4.0427. Min Range: -4.0427

Max Act: 4.0176. Min Act: -0.1700

Data Index: 213248 (Open Web Text)

Max Activating Token Index: 664

Text #1

Max Range: 4.0427. Min Range: -4.0427

Max Act: 4.0427. Min Act: -0.1700

Data Index: 7546370 (Open Web Text)

Max Activating Token Index: 20

Text #2

Max Range: 4.0427. Min Range: -4.0427

Max Act: 3.8522. Min Act: -0.1700

Data Index: 7824152 (Open Web Text)

Max Activating Token Index: 383

Text #3

Max Range: 4.0427. Min Range: -4.0427

Max Act: 3.8787. Min Act: -0.1700

Data Index: 2495562 (Open Web Text)

Max Activating Token Index: 1004

Text #4

Max Range: 4.0427. Min Range: -4.0427

Max Act: 3.8276. Min Act: -0.1700

Data Index: 7273995 (Open Web Text)

Max Activating Token Index: 213

Text #5

Max Range: 4.0427. Min Range: -4.0427

Max Act: 3.8325. Min Act: -0.1700

Data Index: 3447447 (Open Web Text)

Max Activating Token Index: 28

Text #6

Max Range: 4.0427. Min Range: -4.0427

Max Act: 3.8314. Min Act: -0.1700

Data Index: 8222811 (Open Web Text)

Max Activating Token Index: 825

Text #7

Max Range: 4.0427. Min Range: -4.0427

Max Act: 3.8058. Min Act: -0.1700

Data Index: 2821308 (Open Web Text)

Max Activating Token Index: 664

Text #8

Max Range: 4.0427. Min Range: -4.0427

Max Act: 3.7960. Min Act: -0.1700

Data Index: 4264762 (Open Web Text)

Max Activating Token Index: 991

Text #9

Max Range: 4.0427. Min Range: -4.0427

Max Act: 3.7857. Min Act: -0.1700

Data Index: 4263458 (Open Web Text)

Max Activating Token Index: 387

Text #10

Max Range: 4.0427. Min Range: -4.0427

Max Act: 3.7813. Min Act: -0.1700

Data Index: 1501450 (Open Web Text)

Max Activating Token Index: 9

Text #11

Max Range: 4.0427. Min Range: -4.0427

Max Act: 3.7494. Min Act: -0.1700

Data Index: 4762077 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 4.0427. Min Range: -4.0427

Max Act: 3.7469. Min Act: -0.1700

Data Index: 2184959 (Open Web Text)

Max Activating Token Index: 48

Text #13

Max Range: 4.0427. Min Range: -4.0427

Max Act: 3.7416. Min Act: -0.1700

Data Index: 411797 (Open Web Text)

Max Activating Token Index: 531

Text #14

Max Range: 4.0427. Min Range: -4.0427

Max Act: 3.7130. Min Act: -0.1700

Data Index: 5339477 (Open Web Text)

Max Activating Token Index: 460

Text #15

Max Range: 4.0427. Min Range: -4.0427

Max Act: 3.7244. Min Act: -0.1700

Data Index: 5723981 (Open Web Text)

Max Activating Token Index: 58

Text #16

Max Range: 4.0427. Min Range: -4.0427

Max Act: 3.7170. Min Act: -0.1700

Data Index: 448473 (Open Web Text)

Max Activating Token Index: 333

Text #17

Max Range: 4.0427. Min Range: -4.0427

Max Act: 3.7259. Min Act: -0.1700

Data Index: 802265 (Open Web Text)

Max Activating Token Index: 991

Text #18

Max Range: 4.0427. Min Range: -4.0427

Max Act: 3.7089. Min Act: -0.1700

Data Index: 913606 (Open Web Text)

Max Activating Token Index: 568

Text #19

Max Range: 4.0427. Min Range: -4.0427

Max Act: 3.6942. Min Act: -0.1700

Data Index: 7913752 (Open Web Text)

Max Activating Token Index: 842