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

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

Neuron 1289 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: 5.8925. Min Range: -5.8925

Max Act: 5.8925. Min Act: -0.1700

Data Index: 1563798 (Python Code)

Max Activating Token Index: 459

Text #1

Max Range: 5.8925. Min Range: -5.8925

Max Act: 5.8300. Min Act: -0.1700

Data Index: 1529253 (Python Code)

Max Activating Token Index: 492

Text #2

Max Range: 5.8925. Min Range: -5.8925

Max Act: 5.8613. Min Act: -0.1700

Data Index: 1372042 (Python Code)

Max Activating Token Index: 825

Text #3

Max Range: 5.8925. Min Range: -5.8925

Max Act: 5.8300. Min Act: -0.1700

Data Index: 1364430 (Python Code)

Max Activating Token Index: 715

Text #4

Max Range: 5.8925. Min Range: -5.8925

Max Act: 5.7363. Min Act: -0.1700

Data Index: 1486668 (Python Code)

Max Activating Token Index: 647

Text #5

Max Range: 5.8925. Min Range: -5.8925

Max Act: 5.7363. Min Act: -0.1700

Data Index: 1372643 (Python Code)

Max Activating Token Index: 690

Text #6

Max Range: 5.8925. Min Range: -5.8925

Max Act: 5.6738. Min Act: -0.1700

Data Index: 1530033 (Python Code)

Max Activating Token Index: 878

Text #7

Max Range: 5.8925. Min Range: -5.8925

Max Act: 5.7050. Min Act: -0.1700

Data Index: 1642245 (Python Code)

Max Activating Token Index: 685

Text #8

Max Range: 5.8925. Min Range: -5.8925

Max Act: 5.7050. Min Act: -0.1700

Data Index: 1572858 (Python Code)

Max Activating Token Index: 530

Text #9

Max Range: 5.8925. Min Range: -5.8925

Max Act: 5.5800. Min Act: -0.1700

Data Index: 1585966 (Python Code)

Max Activating Token Index: 449

Text #10

Max Range: 5.8925. Min Range: -5.8925

Max Act: 5.6738. Min Act: -0.1700

Data Index: 1529074 (Python Code)

Max Activating Token Index: 479

Text #11

Max Range: 5.8925. Min Range: -5.8925

Max Act: 5.6113. Min Act: -0.1700

Data Index: 1523966 (Python Code)

Max Activating Token Index: 602

Text #12

Max Range: 5.8925. Min Range: -5.8925

Max Act: 5.6425. Min Act: -0.1700

Data Index: 1485003 (Python Code)

Max Activating Token Index: 687

Text #13

Max Range: 5.8925. Min Range: -5.8925

Max Act: 5.5800. Min Act: -0.1700

Data Index: 1503732 (Python Code)

Max Activating Token Index: 713

Text #14

Max Range: 5.8925. Min Range: -5.8925

Max Act: 5.5800. Min Act: -0.1700

Data Index: 1517889 (Python Code)

Max Activating Token Index: 493

Text #15

Max Range: 5.8925. Min Range: -5.8925

Max Act: 5.6113. Min Act: -0.1700

Data Index: 1581043 (Python Code)

Max Activating Token Index: 776

Text #16

Max Range: 5.8925. Min Range: -5.8925

Max Act: 5.5488. Min Act: -0.1700

Data Index: 1646439 (Python Code)

Max Activating Token Index: 437

Text #17

Max Range: 5.8925. Min Range: -5.8925

Max Act: 5.5488. Min Act: -0.1700

Data Index: 1608506 (Python Code)

Max Activating Token Index: 720

Text #18

Max Range: 5.8925. Min Range: -5.8925

Max Act: 5.5175. Min Act: -0.1700

Data Index: 1647268 (Python Code)

Max Activating Token Index: 459

Text #19

Max Range: 5.8925. Min Range: -5.8925

Max Act: 5.4863. Min Act: -0.1700

Data Index: 1637660 (Python Code)

Max Activating Token Index: 1000