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

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

Neuron 426 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6021. Min Range: -5.6021

Max Act: 5.6021. Min Act: -0.1700

Data Index: 1027544 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 5.6021. Min Range: -5.6021

Max Act: 5.5083. Min Act: -0.1700

Data Index: 558358 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 5.6021. Min Range: -5.6021

Max Act: 5.6021. Min Act: -0.1700

Data Index: 263433 (C4 (Web Text))

Max Activating Token Index: 973

Text #3

Max Range: 5.6021. Min Range: -5.6021

Max Act: 5.4458. Min Act: -0.1700

Data Index: 1110213 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 5.6021. Min Range: -5.6021

Max Act: 5.3208. Min Act: -0.1700

Data Index: 83192 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 5.6021. Min Range: -5.6021

Max Act: 5.3208. Min Act: -0.1700

Data Index: 614554 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 5.6021. Min Range: -5.6021

Max Act: 5.3208. Min Act: -0.1700

Data Index: 1128653 (C4 (Web Text))

Max Activating Token Index: 143

Text #7

Max Range: 5.6021. Min Range: -5.6021

Max Act: 5.2583. Min Act: -0.1700

Data Index: 754578 (C4 (Web Text))

Max Activating Token Index: 942

Text #8

Max Range: 5.6021. Min Range: -5.6021

Max Act: 5.2583. Min Act: -0.1700

Data Index: 915570 (C4 (Web Text))

Max Activating Token Index: 377

Text #9

Max Range: 5.6021. Min Range: -5.6021

Max Act: 5.1958. Min Act: -0.1697

Data Index: 891155 (C4 (Web Text))

Max Activating Token Index: 547

Text #10

Max Range: 5.6021. Min Range: -5.6021

Max Act: 5.1021. Min Act: -0.1700

Data Index: 802498 (C4 (Web Text))

Max Activating Token Index: 509

Text #11

Max Range: 5.6021. Min Range: -5.6021

Max Act: 5.1333. Min Act: -0.1700

Data Index: 780629 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 5.6021. Min Range: -5.6021

Max Act: 5.1333. Min Act: -0.1700

Data Index: 1048395 (C4 (Web Text))

Max Activating Token Index: 121

Text #13

Max Range: 5.6021. Min Range: -5.6021

Max Act: 5.1646. Min Act: -0.1700

Data Index: 542158 (C4 (Web Text))

Max Activating Token Index: 651

Text #14

Max Range: 5.6021. Min Range: -5.6021

Max Act: 5.1021. Min Act: -0.1700

Data Index: 266351 (C4 (Web Text))

Max Activating Token Index: 876

Text #15

Max Range: 5.6021. Min Range: -5.6021

Max Act: 5.0708. Min Act: -0.1700

Data Index: 1108006 (C4 (Web Text))

Max Activating Token Index: 334

Text #16

Max Range: 5.6021. Min Range: -5.6021

Max Act: 5.1333. Min Act: -0.1700

Data Index: 553646 (C4 (Web Text))

Max Activating Token Index: 639

Text #17

Max Range: 5.6021. Min Range: -5.6021

Max Act: 5.0396. Min Act: -0.1700

Data Index: 137673 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 5.6021. Min Range: -5.6021

Max Act: 5.1021. Min Act: -0.1700

Data Index: 1009553 (C4 (Web Text))

Max Activating Token Index: 949

Text #19

Max Range: 5.6021. Min Range: -5.6021

Max Act: 5.0396. Min Act: -0.1700

Data Index: 168107 (C4 (Web Text))

Max Activating Token Index: 582