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

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

Neuron 130 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: 5.0729. Min Range: -5.0729

Max Act: 5.0729. Min Act: -0.1699

Data Index: 1214003 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 5.0729. Min Range: -5.0729

Max Act: 5.0416. Min Act: -0.1700

Data Index: 464256 (C4 (Web Text))

Max Activating Token Index: 790

Text #2

Max Range: 5.0729. Min Range: -5.0729

Max Act: 4.9166. Min Act: -0.1700

Data Index: 1246419 (C4 (Web Text))

Max Activating Token Index: 754

Text #3

Max Range: 5.0729. Min Range: -5.0729

Max Act: 4.9791. Min Act: -0.1700

Data Index: 57604 (C4 (Web Text))

Max Activating Token Index: 335

Text #4

Max Range: 5.0729. Min Range: -5.0729

Max Act: 4.9166. Min Act: -0.1700

Data Index: 281828 (C4 (Web Text))

Max Activating Token Index: 285

Text #5

Max Range: 5.0729. Min Range: -5.0729

Max Act: 4.9322. Min Act: -0.1700

Data Index: 959372 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 5.0729. Min Range: -5.0729

Max Act: 4.9166. Min Act: -0.1700

Data Index: 1339160 (C4 (Web Text))

Max Activating Token Index: 886

Text #7

Max Range: 5.0729. Min Range: -5.0729

Max Act: 4.9010. Min Act: -0.1700

Data Index: 733173 (C4 (Web Text))

Max Activating Token Index: 582

Text #8

Max Range: 5.0729. Min Range: -5.0729

Max Act: 4.8541. Min Act: -0.1700

Data Index: 146071 (C4 (Web Text))

Max Activating Token Index: 440

Text #9

Max Range: 5.0729. Min Range: -5.0729

Max Act: 4.9479. Min Act: -0.1700

Data Index: 458250 (C4 (Web Text))

Max Activating Token Index: 775

Text #10

Max Range: 5.0729. Min Range: -5.0729

Max Act: 4.8853. Min Act: -0.1700

Data Index: 64715 (C4 (Web Text))

Max Activating Token Index: 685

Text #11

Max Range: 5.0729. Min Range: -5.0729

Max Act: 4.8853. Min Act: -0.1700

Data Index: 456965 (C4 (Web Text))

Max Activating Token Index: 769

Text #12

Max Range: 5.0729. Min Range: -5.0729

Max Act: 4.8541. Min Act: -0.1700

Data Index: 88333 (C4 (Web Text))

Max Activating Token Index: 412

Text #13

Max Range: 5.0729. Min Range: -5.0729

Max Act: 4.8853. Min Act: -0.1700

Data Index: 677890 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 5.0729. Min Range: -5.0729

Max Act: 4.8541. Min Act: -0.1700

Data Index: 171220 (C4 (Web Text))

Max Activating Token Index: 653

Text #15

Max Range: 5.0729. Min Range: -5.0729

Max Act: 4.8697. Min Act: -0.1700

Data Index: 464011 (C4 (Web Text))

Max Activating Token Index: 121

Text #16

Max Range: 5.0729. Min Range: -5.0729

Max Act: 4.8228. Min Act: -0.1700

Data Index: 1303051 (C4 (Web Text))

Max Activating Token Index: 573

Text #17

Max Range: 5.0729. Min Range: -5.0729

Max Act: 4.8541. Min Act: -0.1700

Data Index: 1078054 (C4 (Web Text))

Max Activating Token Index: 780

Text #18

Max Range: 5.0729. Min Range: -5.0729

Max Act: 4.9322. Min Act: -0.1700

Data Index: 696400 (C4 (Web Text))

Max Activating Token Index: 880

Text #19

Max Range: 5.0729. Min Range: -5.0729

Max Act: 4.8541. Min Act: -0.1700

Data Index: 146988 (C4 (Web Text))

Max Activating Token Index: 831