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

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

Neuron 13 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.2148. Min Range: -6.2148

Max Act: 6.2148. Min Act: -0.1700

Data Index: 42540 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 6.2148. Min Range: -6.2148

Max Act: 6.1523. Min Act: -0.1700

Data Index: 213675 (C4 (Web Text))

Max Activating Token Index: 840

Text #2

Max Range: 6.2148. Min Range: -6.2148

Max Act: 6.1836. Min Act: -0.1700

Data Index: 77073 (C4 (Web Text))

Max Activating Token Index: 678

Text #3

Max Range: 6.2148. Min Range: -6.2148

Max Act: 5.9648. Min Act: -0.1700

Data Index: 477498 (C4 (Web Text))

Max Activating Token Index: 894

Text #4

Max Range: 6.2148. Min Range: -6.2148

Max Act: 6.0898. Min Act: -0.1700

Data Index: 241376 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 6.2148. Min Range: -6.2148

Max Act: 6.0898. Min Act: -0.1700

Data Index: 931412 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 6.2148. Min Range: -6.2148

Max Act: 6.1836. Min Act: -0.1700

Data Index: 139659 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 6.2148. Min Range: -6.2148

Max Act: 5.9961. Min Act: -0.1700

Data Index: 309464 (C4 (Web Text))

Max Activating Token Index: 403

Text #8

Max Range: 6.2148. Min Range: -6.2148

Max Act: 5.9023. Min Act: -0.1700

Data Index: 1042043 (C4 (Web Text))

Max Activating Token Index: 942

Text #9

Max Range: 6.2148. Min Range: -6.2148

Max Act: 5.6523. Min Act: -0.1700

Data Index: 390730 (C4 (Web Text))

Max Activating Token Index: 690

Text #10

Max Range: 6.2148. Min Range: -6.2148

Max Act: 5.7773. Min Act: -0.1700

Data Index: 662272 (C4 (Web Text))

Max Activating Token Index: 661

Text #11

Max Range: 6.2148. Min Range: -6.2148

Max Act: 5.7461. Min Act: -0.1700

Data Index: 706152 (C4 (Web Text))

Max Activating Token Index: 610

Text #12

Max Range: 6.2148. Min Range: -6.2148

Max Act: 5.8711. Min Act: -0.1700

Data Index: 393797 (C4 (Web Text))

Max Activating Token Index: 795

Text #13

Max Range: 6.2148. Min Range: -6.2148

Max Act: 5.9336. Min Act: -0.1700

Data Index: 849568 (C4 (Web Text))

Max Activating Token Index: 465

Text #14

Max Range: 6.2148. Min Range: -6.2148

Max Act: 5.7773. Min Act: -0.1700

Data Index: 256491 (C4 (Web Text))

Max Activating Token Index: 477

Text #15

Max Range: 6.2148. Min Range: -6.2148

Max Act: 5.8711. Min Act: -0.1700

Data Index: 1287246 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 6.2148. Min Range: -6.2148

Max Act: 5.7461. Min Act: -0.1700

Data Index: 350021 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 6.2148. Min Range: -6.2148

Max Act: 5.8086. Min Act: -0.1700

Data Index: 996962 (C4 (Web Text))

Max Activating Token Index: 349

Text #18

Max Range: 6.2148. Min Range: -6.2148

Max Act: 5.6523. Min Act: -0.1700

Data Index: 571225 (C4 (Web Text))

Max Activating Token Index: 887

Text #19

Max Range: 6.2148. Min Range: -6.2148

Max Act: 5.6836. Min Act: -0.1700

Data Index: 360553 (C4 (Web Text))

Max Activating Token Index: 909