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

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

Neuron 1103 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: 3.8656. Min Range: -3.8656

Max Act: 3.8656. Min Act: -0.1700

Data Index: 1259231 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 3.8656. Min Range: -3.8656

Max Act: 3.8343. Min Act: -0.1699

Data Index: 709356 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 3.8656. Min Range: -3.8656

Max Act: 3.7717. Min Act: -0.1699

Data Index: 433374 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 3.8656. Min Range: -3.8656

Max Act: 3.7091. Min Act: -0.1700

Data Index: 393250 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.8656. Min Range: -3.8656

Max Act: 3.7404. Min Act: -0.1700

Data Index: 464223 (C4 (Web Text))

Max Activating Token Index: 465

Text #5

Max Range: 3.8656. Min Range: -3.8656

Max Act: 3.7404. Min Act: -0.1700

Data Index: 252554 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 3.8656. Min Range: -3.8656

Max Act: 3.7404. Min Act: -0.1700

Data Index: 1119679 (C4 (Web Text))

Max Activating Token Index: 588

Text #7

Max Range: 3.8656. Min Range: -3.8656

Max Act: 3.7717. Min Act: -0.1700

Data Index: 672343 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 3.8656. Min Range: -3.8656

Max Act: 3.6778. Min Act: -0.1700

Data Index: 657905 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 3.8656. Min Range: -3.8656

Max Act: 3.6778. Min Act: -0.1700

Data Index: 167967 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 3.8656. Min Range: -3.8656

Max Act: 3.7091. Min Act: -0.1700

Data Index: 1225825 (C4 (Web Text))

Max Activating Token Index: 737

Text #11

Max Range: 3.8656. Min Range: -3.8656

Max Act: 3.6778. Min Act: -0.1700

Data Index: 1315966 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 3.8656. Min Range: -3.8656

Max Act: 3.6465. Min Act: -0.1700

Data Index: 238349 (C4 (Web Text))

Max Activating Token Index: 603

Text #13

Max Range: 3.8656. Min Range: -3.8656

Max Act: 3.6465. Min Act: -0.1700

Data Index: 661589 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 3.8656. Min Range: -3.8656

Max Act: 3.6465. Min Act: -0.1700

Data Index: 102194 (C4 (Web Text))

Max Activating Token Index: 570

Text #15

Max Range: 3.8656. Min Range: -3.8656

Max Act: 3.6152. Min Act: -0.1700

Data Index: 1182368 (C4 (Web Text))

Max Activating Token Index: 16

Text #16

Max Range: 3.8656. Min Range: -3.8656

Max Act: 3.5839. Min Act: -0.1700

Data Index: 435657 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 3.8656. Min Range: -3.8656

Max Act: 3.6152. Min Act: -0.1700

Data Index: 924142 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 3.8656. Min Range: -3.8656

Max Act: 3.6152. Min Act: -0.1700

Data Index: 736434 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 3.8656. Min Range: -3.8656

Max Act: 3.6152. Min Act: -0.1700

Data Index: 632126 (C4 (Web Text))

Max Activating Token Index: 393