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

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

Neuron 122 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: 5.3713. Min Range: -5.3713

Max Act: 5.3713. Min Act: -0.1700

Data Index: 492873 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 5.3713. Min Range: -5.3713

Max Act: 5.1838. Min Act: -0.1700

Data Index: 1077785 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 5.3713. Min Range: -5.3713

Max Act: 5.0588. Min Act: -0.1700

Data Index: 1487022 (Python Code)

Max Activating Token Index: 643

Text #3

Max Range: 5.3713. Min Range: -5.3713

Max Act: 5.0588. Min Act: -0.1700

Data Index: 51833 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 5.3713. Min Range: -5.3713

Max Act: 5.0901. Min Act: -0.1700

Data Index: 243688 (C4 (Web Text))

Max Activating Token Index: 539

Text #5

Max Range: 5.3713. Min Range: -5.3713

Max Act: 4.9963. Min Act: -0.1700

Data Index: 1560222 (Python Code)

Max Activating Token Index: 730

Text #6

Max Range: 5.3713. Min Range: -5.3713

Max Act: 4.9338. Min Act: -0.1700

Data Index: 88993 (C4 (Web Text))

Max Activating Token Index: 717

Text #7

Max Range: 5.3713. Min Range: -5.3713

Max Act: 4.9963. Min Act: -0.1700

Data Index: 1268708 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 5.3713. Min Range: -5.3713

Max Act: 4.9338. Min Act: -0.1700

Data Index: 1179784 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 5.3713. Min Range: -5.3713

Max Act: 4.9651. Min Act: -0.1700

Data Index: 206649 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 5.3713. Min Range: -5.3713

Max Act: 4.9026. Min Act: -0.1700

Data Index: 984439 (C4 (Web Text))

Max Activating Token Index: 452

Text #11

Max Range: 5.3713. Min Range: -5.3713

Max Act: 4.9338. Min Act: -0.1700

Data Index: 607818 (C4 (Web Text))

Max Activating Token Index: 23

Text #12

Max Range: 5.3713. Min Range: -5.3713

Max Act: 4.9026. Min Act: -0.1700

Data Index: 302015 (C4 (Web Text))

Max Activating Token Index: 545

Text #13

Max Range: 5.3713. Min Range: -5.3713

Max Act: 4.8713. Min Act: -0.1700

Data Index: 224737 (C4 (Web Text))

Max Activating Token Index: 656

Text #14

Max Range: 5.3713. Min Range: -5.3713

Max Act: 4.9026. Min Act: -0.1700

Data Index: 1220928 (C4 (Web Text))

Max Activating Token Index: 635

Text #15

Max Range: 5.3713. Min Range: -5.3713

Max Act: 4.9026. Min Act: -0.1700

Data Index: 485871 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 5.3713. Min Range: -5.3713

Max Act: 4.8401. Min Act: -0.1700

Data Index: 275485 (C4 (Web Text))

Max Activating Token Index: 855

Text #17

Max Range: 5.3713. Min Range: -5.3713

Max Act: 4.9338. Min Act: -0.1700

Data Index: 106226 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 5.3713. Min Range: -5.3713

Max Act: 4.8401. Min Act: -0.1700

Data Index: 529069 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 5.3713. Min Range: -5.3713

Max Act: 4.9026. Min Act: -0.1700

Data Index: 796654 (C4 (Web Text))

Max Activating Token Index: 927