Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1747 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 8.9577. Min Range: -8.9577

Max Act: 8.9577. Min Act: -0.1700

Data Index: 495501 (C4 (Web Text))

Max Activating Token Index: 126

Text #1

Max Range: 8.9577. Min Range: -8.9577

Max Act: 8.7702. Min Act: -0.1700

Data Index: 872144 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 8.9577. Min Range: -8.9577

Max Act: 8.8952. Min Act: -0.1700

Data Index: 488292 (C4 (Web Text))

Max Activating Token Index: 484

Text #3

Max Range: 8.9577. Min Range: -8.9577

Max Act: 8.6452. Min Act: -0.1700

Data Index: 768014 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 8.9577. Min Range: -8.9577

Max Act: 8.5202. Min Act: -0.1700

Data Index: 1148061 (C4 (Web Text))

Max Activating Token Index: 413

Text #5

Max Range: 8.9577. Min Range: -8.9577

Max Act: 8.3327. Min Act: -0.1700

Data Index: 1015964 (C4 (Web Text))

Max Activating Token Index: 531

Text #6

Max Range: 8.9577. Min Range: -8.9577

Max Act: 8.2702. Min Act: -0.1700

Data Index: 8239 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 8.9577. Min Range: -8.9577

Max Act: 8.3327. Min Act: -0.1700

Data Index: 757543 (C4 (Web Text))

Max Activating Token Index: 322

Text #8

Max Range: 8.9577. Min Range: -8.9577

Max Act: 8.1452. Min Act: -0.1700

Data Index: 102340 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 8.9577. Min Range: -8.9577

Max Act: 8.2077. Min Act: -0.1700

Data Index: 535396 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 8.9577. Min Range: -8.9577

Max Act: 8.0827. Min Act: -0.1700

Data Index: 619122 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 8.9577. Min Range: -8.9577

Max Act: 8.3327. Min Act: -0.1700

Data Index: 982967 (C4 (Web Text))

Max Activating Token Index: 456

Text #12

Max Range: 8.9577. Min Range: -8.9577

Max Act: 8.2702. Min Act: -0.1700

Data Index: 775313 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 8.9577. Min Range: -8.9577

Max Act: 8.2702. Min Act: -0.1700

Data Index: 783871 (C4 (Web Text))

Max Activating Token Index: 565

Text #14

Max Range: 8.9577. Min Range: -8.9577

Max Act: 8.0827. Min Act: -0.1700

Data Index: 171680 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 8.9577. Min Range: -8.9577

Max Act: 8.0827. Min Act: -0.1700

Data Index: 155679 (C4 (Web Text))

Max Activating Token Index: 490

Text #16

Max Range: 8.9577. Min Range: -8.9577

Max Act: 8.1452. Min Act: -0.1700

Data Index: 512130 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 8.9577. Min Range: -8.9577

Max Act: 8.1452. Min Act: -0.1700

Data Index: 199213 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 8.9577. Min Range: -8.9577

Max Act: 8.0827. Min Act: -0.1700

Data Index: 269726 (C4 (Web Text))

Max Activating Token Index: 585

Text #19

Max Range: 8.9577. Min Range: -8.9577

Max Act: 8.0827. Min Act: -0.1700

Data Index: 238984 (C4 (Web Text))

Max Activating Token Index: 387