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

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

Neuron 1121 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: 4.3360. Min Range: -4.3360

Max Act: 4.3360. Min Act: -0.1700

Data Index: 1408828 (Python Code)

Max Activating Token Index: 976

Text #1

Max Range: 4.3360. Min Range: -4.3360

Max Act: 4.1797. Min Act: -0.1700

Data Index: 169994 (C4 (Web Text))

Max Activating Token Index: 704

Text #2

Max Range: 4.3360. Min Range: -4.3360

Max Act: 4.0860. Min Act: -0.1700

Data Index: 847434 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 4.3360. Min Range: -4.3360

Max Act: 4.0078. Min Act: -0.1700

Data Index: 996482 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 4.3360. Min Range: -4.3360

Max Act: 4.0234. Min Act: -0.1700

Data Index: 732426 (C4 (Web Text))

Max Activating Token Index: 999

Text #5

Max Range: 4.3360. Min Range: -4.3360

Max Act: 3.9922. Min Act: -0.1700

Data Index: 1285221 (C4 (Web Text))

Max Activating Token Index: 884

Text #6

Max Range: 4.3360. Min Range: -4.3360

Max Act: 3.9922. Min Act: -0.1700

Data Index: 1003655 (C4 (Web Text))

Max Activating Token Index: 175

Text #7

Max Range: 4.3360. Min Range: -4.3360

Max Act: 3.9922. Min Act: -0.1700

Data Index: 860136 (C4 (Web Text))

Max Activating Token Index: 352

Text #8

Max Range: 4.3360. Min Range: -4.3360

Max Act: 3.9609. Min Act: -0.1700

Data Index: 1104073 (C4 (Web Text))

Max Activating Token Index: 622

Text #9

Max Range: 4.3360. Min Range: -4.3360

Max Act: 3.9609. Min Act: -0.1700

Data Index: 170640 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 4.3360. Min Range: -4.3360

Max Act: 3.9140. Min Act: -0.1700

Data Index: 1120854 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 4.3360. Min Range: -4.3360

Max Act: 3.8984. Min Act: -0.1700

Data Index: 879048 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 4.3360. Min Range: -4.3360

Max Act: 3.8827. Min Act: -0.1700

Data Index: 361589 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 4.3360. Min Range: -4.3360

Max Act: 3.8514. Min Act: -0.1700

Data Index: 1348894 (C4 (Web Text))

Max Activating Token Index: 424

Text #14

Max Range: 4.3360. Min Range: -4.3360

Max Act: 3.8358. Min Act: -0.1700

Data Index: 220523 (C4 (Web Text))

Max Activating Token Index: 738

Text #15

Max Range: 4.3360. Min Range: -4.3360

Max Act: 3.8045. Min Act: -0.1700

Data Index: 187666 (C4 (Web Text))

Max Activating Token Index: 334

Text #16

Max Range: 4.3360. Min Range: -4.3360

Max Act: 3.8514. Min Act: -0.1700

Data Index: 301025 (C4 (Web Text))

Max Activating Token Index: 238

Text #17

Max Range: 4.3360. Min Range: -4.3360

Max Act: 3.8202. Min Act: -0.1700

Data Index: 681661 (C4 (Web Text))

Max Activating Token Index: 657

Text #18

Max Range: 4.3360. Min Range: -4.3360

Max Act: 3.8202. Min Act: -0.1700

Data Index: 1433610 (Python Code)

Max Activating Token Index: 741

Text #19

Max Range: 4.3360. Min Range: -4.3360

Max Act: 3.7732. Min Act: -0.1700

Data Index: 109693 (C4 (Web Text))

Max Activating Token Index: 976