Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 156 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.7035. Min Range: -5.7035

Max Act: 5.7035. Min Act: -0.1700

Data Index: 1219294 (C4 (Web Text))

Max Activating Token Index: 379

Text #1

Max Range: 5.7035. Min Range: -5.7035

Max Act: 5.4847. Min Act: -0.1700

Data Index: 1241797 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 5.7035. Min Range: -5.7035

Max Act: 5.4535. Min Act: -0.1700

Data Index: 868152 (C4 (Web Text))

Max Activating Token Index: 773

Text #3

Max Range: 5.7035. Min Range: -5.7035

Max Act: 5.3910. Min Act: -0.1700

Data Index: 1143871 (C4 (Web Text))

Max Activating Token Index: 964

Text #4

Max Range: 5.7035. Min Range: -5.7035

Max Act: 5.2660. Min Act: -0.1700

Data Index: 234182 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 5.7035. Min Range: -5.7035

Max Act: 5.2972. Min Act: -0.1700

Data Index: 993515 (C4 (Web Text))

Max Activating Token Index: 680

Text #6

Max Range: 5.7035. Min Range: -5.7035

Max Act: 5.2660. Min Act: -0.1700

Data Index: 272619 (C4 (Web Text))

Max Activating Token Index: 755

Text #7

Max Range: 5.7035. Min Range: -5.7035

Max Act: 5.2347. Min Act: -0.1700

Data Index: 1014159 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 5.7035. Min Range: -5.7035

Max Act: 5.2035. Min Act: -0.1700

Data Index: 843330 (C4 (Web Text))

Max Activating Token Index: 72

Text #9

Max Range: 5.7035. Min Range: -5.7035

Max Act: 5.1722. Min Act: -0.1700

Data Index: 1295699 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 5.7035. Min Range: -5.7035

Max Act: 5.2347. Min Act: -0.1700

Data Index: 156223 (C4 (Web Text))

Max Activating Token Index: 487

Text #11

Max Range: 5.7035. Min Range: -5.7035

Max Act: 5.1410. Min Act: -0.1700

Data Index: 967411 (C4 (Web Text))

Max Activating Token Index: 321

Text #12

Max Range: 5.7035. Min Range: -5.7035

Max Act: 5.1410. Min Act: -0.1700

Data Index: 847055 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 5.7035. Min Range: -5.7035

Max Act: 5.1097. Min Act: -0.1700

Data Index: 13985 (C4 (Web Text))

Max Activating Token Index: 959

Text #14

Max Range: 5.7035. Min Range: -5.7035

Max Act: 5.1722. Min Act: -0.1700

Data Index: 1022613 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 5.7035. Min Range: -5.7035

Max Act: 5.1097. Min Act: -0.1700

Data Index: 677425 (C4 (Web Text))

Max Activating Token Index: 533

Text #16

Max Range: 5.7035. Min Range: -5.7035

Max Act: 5.1097. Min Act: -0.1700

Data Index: 42498 (C4 (Web Text))

Max Activating Token Index: 692

Text #17

Max Range: 5.7035. Min Range: -5.7035

Max Act: 5.1097. Min Act: -0.1700

Data Index: 1233663 (C4 (Web Text))

Max Activating Token Index: 826

Text #18

Max Range: 5.7035. Min Range: -5.7035

Max Act: 5.0785. Min Act: -0.1700

Data Index: 1260861 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 5.7035. Min Range: -5.7035

Max Act: 5.0785. Min Act: -0.1700

Data Index: 67387 (C4 (Web Text))

Max Activating Token Index: 75