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

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

Neuron 158 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5624. Min Range: -3.5624

Max Act: 3.5624. Min Act: -0.1700

Data Index: 308600 (C4 (Web Text))

Max Activating Token Index: 533

Text #1

Max Range: 3.5624. Min Range: -3.5624

Max Act: 3.3900. Min Act: -0.1700

Data Index: 774108 (C4 (Web Text))

Max Activating Token Index: 873

Text #2

Max Range: 3.5624. Min Range: -3.5624

Max Act: 3.3743. Min Act: -0.1700

Data Index: 776174 (C4 (Web Text))

Max Activating Token Index: 364

Text #3

Max Range: 3.5624. Min Range: -3.5624

Max Act: 3.3429. Min Act: -0.1700

Data Index: 576588 (C4 (Web Text))

Max Activating Token Index: 8

Text #4

Max Range: 3.5624. Min Range: -3.5624

Max Act: 3.3429. Min Act: -0.1700

Data Index: 211283 (C4 (Web Text))

Max Activating Token Index: 579

Text #5

Max Range: 3.5624. Min Range: -3.5624

Max Act: 3.3429. Min Act: -0.1700

Data Index: 951190 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 3.5624. Min Range: -3.5624

Max Act: 3.3429. Min Act: -0.1700

Data Index: 1115582 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 3.5624. Min Range: -3.5624

Max Act: 3.3429. Min Act: -0.1700

Data Index: 667744 (C4 (Web Text))

Max Activating Token Index: 985

Text #8

Max Range: 3.5624. Min Range: -3.5624

Max Act: 3.3115. Min Act: -0.1700

Data Index: 432373 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 3.5624. Min Range: -3.5624

Max Act: 3.2644. Min Act: -0.1698

Data Index: 1540252 (Python Code)

Max Activating Token Index: 7

Text #10

Max Range: 3.5624. Min Range: -3.5624

Max Act: 3.2801. Min Act: -0.1700

Data Index: 261890 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 3.5624. Min Range: -3.5624

Max Act: 3.2801. Min Act: -0.1700

Data Index: 1279526 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 3.5624. Min Range: -3.5624

Max Act: 3.2644. Min Act: -0.1700

Data Index: 1007548 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 3.5624. Min Range: -3.5624

Max Act: 3.2958. Min Act: -0.1700

Data Index: 992062 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 3.5624. Min Range: -3.5624

Max Act: 3.2801. Min Act: -0.1700

Data Index: 1085527 (C4 (Web Text))

Max Activating Token Index: 517

Text #15

Max Range: 3.5624. Min Range: -3.5624

Max Act: 3.2644. Min Act: -0.1700

Data Index: 795963 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 3.5624. Min Range: -3.5624

Max Act: 3.2644. Min Act: -0.1700

Data Index: 676828 (C4 (Web Text))

Max Activating Token Index: 992

Text #17

Max Range: 3.5624. Min Range: -3.5624

Max Act: 3.2644. Min Act: -0.1700

Data Index: 894387 (C4 (Web Text))

Max Activating Token Index: 325

Text #18

Max Range: 3.5624. Min Range: -3.5624

Max Act: 3.2487. Min Act: -0.1700

Data Index: 974657 (C4 (Web Text))

Max Activating Token Index: 6

Text #19

Max Range: 3.5624. Min Range: -3.5624

Max Act: 3.2644. Min Act: -0.1700

Data Index: 1595723 (Python Code)

Max Activating Token Index: 421