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

Dataset: Open Web Text

Neuron 1001 in Layer 3

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: 3.0475. Min Range: -3.0475

Max Act: 3.0475. Min Act: -0.1700

Data Index: 1144461 (Open Web Text)

Max Activating Token Index: 73

Text #1

Max Range: 3.0475. Min Range: -3.0475

Max Act: 2.9067. Min Act: -0.1700

Data Index: 7463215 (Open Web Text)

Max Activating Token Index: 521

Text #2

Max Range: 3.0475. Min Range: -3.0475

Max Act: 2.9421. Min Act: -0.1700

Data Index: 16077 (Open Web Text)

Max Activating Token Index: 948

Text #3

Max Range: 3.0475. Min Range: -3.0475

Max Act: 2.9555. Min Act: -0.1700

Data Index: 2251378 (Open Web Text)

Max Activating Token Index: 20

Text #4

Max Range: 3.0475. Min Range: -3.0475

Max Act: 2.9284. Min Act: -0.1700

Data Index: 1623479 (Open Web Text)

Max Activating Token Index: 95

Text #5

Max Range: 3.0475. Min Range: -3.0475

Max Act: 2.9016. Min Act: -0.1700

Data Index: 2071123 (Open Web Text)

Max Activating Token Index: 756

Text #6

Max Range: 3.0475. Min Range: -3.0475

Max Act: 2.9099. Min Act: -0.1700

Data Index: 3258423 (Open Web Text)

Max Activating Token Index: 864

Text #7

Max Range: 3.0475. Min Range: -3.0475

Max Act: 2.9194. Min Act: -0.1700

Data Index: 3427002 (Open Web Text)

Max Activating Token Index: 451

Text #8

Max Range: 3.0475. Min Range: -3.0475

Max Act: 2.8940. Min Act: -0.1700

Data Index: 1784708 (Open Web Text)

Max Activating Token Index: 706

Text #9

Max Range: 3.0475. Min Range: -3.0475

Max Act: 2.8516. Min Act: -0.1700

Data Index: 462541 (Open Web Text)

Max Activating Token Index: 891

Text #10

Max Range: 3.0475. Min Range: -3.0475

Max Act: 2.8685. Min Act: -0.1700

Data Index: 8669960 (Open Web Text)

Max Activating Token Index: 901

Text #11

Max Range: 3.0475. Min Range: -3.0475

Max Act: 2.8408. Min Act: -0.1700

Data Index: 2991211 (Open Web Text)

Max Activating Token Index: 55

Text #12

Max Range: 3.0475. Min Range: -3.0475

Max Act: 2.8020. Min Act: -0.1700

Data Index: 4678523 (Open Web Text)

Max Activating Token Index: 411

Text #13

Max Range: 3.0475. Min Range: -3.0475

Max Act: 2.8010. Min Act: -0.1700

Data Index: 2190041 (Open Web Text)

Max Activating Token Index: 149

Text #14

Max Range: 3.0475. Min Range: -3.0475

Max Act: 2.8321. Min Act: -0.1700

Data Index: 2393027 (Open Web Text)

Max Activating Token Index: 211

Text #15

Max Range: 3.0475. Min Range: -3.0475

Max Act: 2.8278. Min Act: -0.1700

Data Index: 6044055 (Open Web Text)

Max Activating Token Index: 767

Text #16

Max Range: 3.0475. Min Range: -3.0475

Max Act: 2.8405. Min Act: -0.1700

Data Index: 5707407 (Open Web Text)

Max Activating Token Index: 318

Text #17

Max Range: 3.0475. Min Range: -3.0475

Max Act: 2.8110. Min Act: -0.1700

Data Index: 5227944 (Open Web Text)

Max Activating Token Index: 756

Text #18

Max Range: 3.0475. Min Range: -3.0475

Max Act: 2.8031. Min Act: -0.1700

Data Index: 6096082 (Open Web Text)

Max Activating Token Index: 127

Text #19

Max Range: 3.0475. Min Range: -3.0475

Max Act: 2.7754. Min Act: -0.1700

Data Index: 2199732 (Open Web Text)

Max Activating Token Index: 535