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

Dataset: Open Web Text

Neuron 2741 in Layer 0

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: 4.8168. Min Range: -4.8168

Max Act: 4.8168. Min Act: -0.1700

Data Index: 6728678 (Open Web Text)

Max Activating Token Index: 645

Text #1

Max Range: 4.8168. Min Range: -4.8168

Max Act: 4.7052. Min Act: -0.1700

Data Index: 891944 (Open Web Text)

Max Activating Token Index: 13

Text #2

Max Range: 4.8168. Min Range: -4.8168

Max Act: 4.7063. Min Act: -0.1700

Data Index: 2644913 (Open Web Text)

Max Activating Token Index: 722

Text #3

Max Range: 4.8168. Min Range: -4.8168

Max Act: 4.6829. Min Act: -0.1700

Data Index: 5850279 (Open Web Text)

Max Activating Token Index: 10

Text #4

Max Range: 4.8168. Min Range: -4.8168

Max Act: 4.6923. Min Act: -0.1700

Data Index: 3734598 (Open Web Text)

Max Activating Token Index: 719

Text #5

Max Range: 4.8168. Min Range: -4.8168

Max Act: 4.7053. Min Act: -0.1700

Data Index: 777390 (Open Web Text)

Max Activating Token Index: 10

Text #6

Max Range: 4.8168. Min Range: -4.8168

Max Act: 4.6493. Min Act: -0.1700

Data Index: 4237383 (Open Web Text)

Max Activating Token Index: 341

Text #7

Max Range: 4.8168. Min Range: -4.8168

Max Act: 4.6697. Min Act: -0.1700

Data Index: 3891616 (Open Web Text)

Max Activating Token Index: 789

Text #8

Max Range: 4.8168. Min Range: -4.8168

Max Act: 4.6713. Min Act: -0.1700

Data Index: 2368717 (Open Web Text)

Max Activating Token Index: 797

Text #9

Max Range: 4.8168. Min Range: -4.8168

Max Act: 4.6787. Min Act: -0.1700

Data Index: 200938 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 4.8168. Min Range: -4.8168

Max Act: 4.6549. Min Act: -0.1700

Data Index: 3637308 (Open Web Text)

Max Activating Token Index: 10

Text #11

Max Range: 4.8168. Min Range: -4.8168

Max Act: 4.6630. Min Act: -0.1700

Data Index: 3538385 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 4.8168. Min Range: -4.8168

Max Act: 4.6712. Min Act: -0.1700

Data Index: 7530686 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 4.8168. Min Range: -4.8168

Max Act: 4.6646. Min Act: -0.1700

Data Index: 6758733 (Open Web Text)

Max Activating Token Index: 10

Text #14

Max Range: 4.8168. Min Range: -4.8168

Max Act: 4.6633. Min Act: -0.1700

Data Index: 1550191 (Open Web Text)

Max Activating Token Index: 14

Text #15

Max Range: 4.8168. Min Range: -4.8168

Max Act: 4.6573. Min Act: -0.1700

Data Index: 3061502 (Open Web Text)

Max Activating Token Index: 27

Text #16

Max Range: 4.8168. Min Range: -4.8168

Max Act: 4.6682. Min Act: -0.1700

Data Index: 209799 (Open Web Text)

Max Activating Token Index: 10

Text #17

Max Range: 4.8168. Min Range: -4.8168

Max Act: 4.6257. Min Act: -0.1700

Data Index: 3474993 (Open Web Text)

Max Activating Token Index: 632

Text #18

Max Range: 4.8168. Min Range: -4.8168

Max Act: 4.6327. Min Act: -0.1700

Data Index: 1802856 (Open Web Text)

Max Activating Token Index: 134

Text #19

Max Range: 4.8168. Min Range: -4.8168

Max Act: 4.6371. Min Act: -0.1700

Data Index: 3845460 (Open Web Text)

Max Activating Token Index: 6