Model: GELU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1967 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 4.9410. Min Range: -4.9410

Max Act: 4.9410. Min Act: -0.1700

Data Index: 393948 (C4 (Web Text))

Max Activating Token Index: 640

Text #1

Max Range: 4.9410. Min Range: -4.9410

Max Act: 4.9097. Min Act: -0.1700

Data Index: 1127673 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 4.9410. Min Range: -4.9410

Max Act: 4.8472. Min Act: -0.1700

Data Index: 1138307 (C4 (Web Text))

Max Activating Token Index: 444

Text #3

Max Range: 4.9410. Min Range: -4.9410

Max Act: 4.7535. Min Act: -0.1700

Data Index: 1233286 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 4.9410. Min Range: -4.9410

Max Act: 4.7222. Min Act: -0.1700

Data Index: 1203209 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 4.9410. Min Range: -4.9410

Max Act: 4.6597. Min Act: -0.1700

Data Index: 708232 (C4 (Web Text))

Max Activating Token Index: 673

Text #6

Max Range: 4.9410. Min Range: -4.9410

Max Act: 4.7535. Min Act: -0.1700

Data Index: 323449 (C4 (Web Text))

Max Activating Token Index: 111

Text #7

Max Range: 4.9410. Min Range: -4.9410

Max Act: 4.6597. Min Act: -0.1700

Data Index: 1236911 (C4 (Web Text))

Max Activating Token Index: 826

Text #8

Max Range: 4.9410. Min Range: -4.9410

Max Act: 4.7222. Min Act: -0.1700

Data Index: 201363 (C4 (Web Text))

Max Activating Token Index: 505

Text #9

Max Range: 4.9410. Min Range: -4.9410

Max Act: 4.7222. Min Act: -0.1700

Data Index: 83481 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 4.9410. Min Range: -4.9410

Max Act: 4.6597. Min Act: -0.1699

Data Index: 5266 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 4.9410. Min Range: -4.9410

Max Act: 4.6285. Min Act: -0.1700

Data Index: 314711 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 4.9410. Min Range: -4.9410

Max Act: 4.6285. Min Act: -0.1700

Data Index: 1136475 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 4.9410. Min Range: -4.9410

Max Act: 4.6597. Min Act: -0.1700

Data Index: 818610 (C4 (Web Text))

Max Activating Token Index: 627

Text #14

Max Range: 4.9410. Min Range: -4.9410

Max Act: 4.6285. Min Act: -0.1700

Data Index: 273740 (C4 (Web Text))

Max Activating Token Index: 758

Text #15

Max Range: 4.9410. Min Range: -4.9410

Max Act: 4.6597. Min Act: -0.1700

Data Index: 84475 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 4.9410. Min Range: -4.9410

Max Act: 4.6285. Min Act: -0.1700

Data Index: 1009985 (C4 (Web Text))

Max Activating Token Index: 141

Text #17

Max Range: 4.9410. Min Range: -4.9410

Max Act: 4.6285. Min Act: -0.1699

Data Index: 584195 (C4 (Web Text))

Max Activating Token Index: 581

Text #18

Max Range: 4.9410. Min Range: -4.9410

Max Act: 4.6285. Min Act: -0.1700

Data Index: 941598 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 4.9410. Min Range: -4.9410

Max Act: 4.5972. Min Act: -0.1700

Data Index: 339340 (C4 (Web Text))

Max Activating Token Index: 32