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

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

Neuron 12 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: 3.2556. Min Range: -3.2556

Max Act: 3.2556. Min Act: -0.1700

Data Index: 50469 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 3.2556. Min Range: -3.2556

Max Act: 3.2084. Min Act: -0.1700

Data Index: 1126412 (C4 (Web Text))

Max Activating Token Index: 846

Text #2

Max Range: 3.2556. Min Range: -3.2556

Max Act: 3.1454. Min Act: -0.1700

Data Index: 31070 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 3.2556. Min Range: -3.2556

Max Act: 3.1297. Min Act: -0.1700

Data Index: 590043 (C4 (Web Text))

Max Activating Token Index: 961

Text #4

Max Range: 3.2556. Min Range: -3.2556

Max Act: 3.1297. Min Act: -0.1700

Data Index: 100922 (C4 (Web Text))

Max Activating Token Index: 627

Text #5

Max Range: 3.2556. Min Range: -3.2556

Max Act: 3.1139. Min Act: -0.1700

Data Index: 806107 (C4 (Web Text))

Max Activating Token Index: 580

Text #6

Max Range: 3.2556. Min Range: -3.2556

Max Act: 3.1297. Min Act: -0.1700

Data Index: 1297489 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 3.2556. Min Range: -3.2556

Max Act: 3.0981. Min Act: -0.1700

Data Index: 1232658 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 3.2556. Min Range: -3.2556

Max Act: 3.0824. Min Act: -0.1700

Data Index: 976992 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 3.2556. Min Range: -3.2556

Max Act: 3.0824. Min Act: -0.1700

Data Index: 558439 (C4 (Web Text))

Max Activating Token Index: 747

Text #10

Max Range: 3.2556. Min Range: -3.2556

Max Act: 3.0824. Min Act: -0.1700

Data Index: 1218216 (C4 (Web Text))

Max Activating Token Index: 886

Text #11

Max Range: 3.2556. Min Range: -3.2556

Max Act: 3.0981. Min Act: -0.1700

Data Index: 332369 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 3.2556. Min Range: -3.2556

Max Act: 3.0824. Min Act: -0.1700

Data Index: 433244 (C4 (Web Text))

Max Activating Token Index: 382

Text #13

Max Range: 3.2556. Min Range: -3.2556

Max Act: 3.0824. Min Act: -0.1700

Data Index: 858377 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 3.2556. Min Range: -3.2556

Max Act: 3.0824. Min Act: -0.1700

Data Index: 475906 (C4 (Web Text))

Max Activating Token Index: 488

Text #15

Max Range: 3.2556. Min Range: -3.2556

Max Act: 3.0666. Min Act: -0.1700

Data Index: 202744 (C4 (Web Text))

Max Activating Token Index: 305

Text #16

Max Range: 3.2556. Min Range: -3.2556

Max Act: 3.0824. Min Act: -0.1700

Data Index: 329165 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 3.2556. Min Range: -3.2556

Max Act: 3.0508. Min Act: -0.1700

Data Index: 534117 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 3.2556. Min Range: -3.2556

Max Act: 3.0824. Min Act: -0.1700

Data Index: 897290 (C4 (Web Text))

Max Activating Token Index: 532

Text #19

Max Range: 3.2556. Min Range: -3.2556

Max Act: 3.0508. Min Act: -0.1700

Data Index: 564434 (C4 (Web Text))

Max Activating Token Index: 163