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

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

Neuron 478 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.7019. Min Range: -3.7019

Max Act: 3.7019. Min Act: -0.1700

Data Index: 1487520 (Python Code)

Max Activating Token Index: 733

Text #1

Max Range: 3.7019. Min Range: -3.7019

Max Act: 3.6236. Min Act: -0.1700

Data Index: 1466207 (Python Code)

Max Activating Token Index: 901

Text #2

Max Range: 3.7019. Min Range: -3.7019

Max Act: 3.6080. Min Act: -0.1700

Data Index: 1593808 (Python Code)

Max Activating Token Index: 15

Text #3

Max Range: 3.7019. Min Range: -3.7019

Max Act: 3.5767. Min Act: -0.1700

Data Index: 1361172 (Python Code)

Max Activating Token Index: 354

Text #4

Max Range: 3.7019. Min Range: -3.7019

Max Act: 3.5767. Min Act: -0.1700

Data Index: 1475373 (Python Code)

Max Activating Token Index: 560

Text #5

Max Range: 3.7019. Min Range: -3.7019

Max Act: 3.5610. Min Act: -0.1700

Data Index: 1649036 (Python Code)

Max Activating Token Index: 52

Text #6

Max Range: 3.7019. Min Range: -3.7019

Max Act: 3.5297. Min Act: -0.1700

Data Index: 1573570 (Python Code)

Max Activating Token Index: 104

Text #7

Max Range: 3.7019. Min Range: -3.7019

Max Act: 3.5297. Min Act: -0.1700

Data Index: 1629512 (Python Code)

Max Activating Token Index: 693

Text #8

Max Range: 3.7019. Min Range: -3.7019

Max Act: 3.4827. Min Act: -0.1700

Data Index: 1604156 (Python Code)

Max Activating Token Index: 305

Text #9

Max Range: 3.7019. Min Range: -3.7019

Max Act: 3.4983. Min Act: -0.1700

Data Index: 1549344 (Python Code)

Max Activating Token Index: 960

Text #10

Max Range: 3.7019. Min Range: -3.7019

Max Act: 3.4670. Min Act: -0.1700

Data Index: 1369857 (Python Code)

Max Activating Token Index: 717

Text #11

Max Range: 3.7019. Min Range: -3.7019

Max Act: 3.4513. Min Act: -0.1700

Data Index: 1426566 (Python Code)

Max Activating Token Index: 219

Text #12

Max Range: 3.7019. Min Range: -3.7019

Max Act: 3.4513. Min Act: -0.1700

Data Index: 1484783 (Python Code)

Max Activating Token Index: 511

Text #13

Max Range: 3.7019. Min Range: -3.7019

Max Act: 3.4513. Min Act: -0.1700

Data Index: 1641033 (Python Code)

Max Activating Token Index: 977

Text #14

Max Range: 3.7019. Min Range: -3.7019

Max Act: 3.4356. Min Act: -0.1700

Data Index: 1472872 (Python Code)

Max Activating Token Index: 597

Text #15

Max Range: 3.7019. Min Range: -3.7019

Max Act: 3.4513. Min Act: -0.1700

Data Index: 1412958 (Python Code)

Max Activating Token Index: 299

Text #16

Max Range: 3.7019. Min Range: -3.7019

Max Act: 3.4356. Min Act: -0.1700

Data Index: 1631094 (Python Code)

Max Activating Token Index: 246

Text #17

Max Range: 3.7019. Min Range: -3.7019

Max Act: 3.4200. Min Act: -0.1700

Data Index: 1495591 (Python Code)

Max Activating Token Index: 845

Text #18

Max Range: 3.7019. Min Range: -3.7019

Max Act: 3.4200. Min Act: -0.1700

Data Index: 1425825 (Python Code)

Max Activating Token Index: 723

Text #19

Max Range: 3.7019. Min Range: -3.7019

Max Act: 3.4356. Min Act: -0.1700

Data Index: 1431344 (Python Code)

Max Activating Token Index: 376