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

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

Neuron 186 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.6660. Min Range: -3.6660

Max Act: 3.6660. Min Act: -0.1700

Data Index: 99122 (C4 (Web Text))

Max Activating Token Index: 321

Text #1

Max Range: 3.6660. Min Range: -3.6660

Max Act: 3.6190. Min Act: -0.1700

Data Index: 442885 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 3.6660. Min Range: -3.6660

Max Act: 3.5094. Min Act: -0.1700

Data Index: 1193874 (C4 (Web Text))

Max Activating Token Index: 1013

Text #3

Max Range: 3.6660. Min Range: -3.6660

Max Act: 3.4781. Min Act: -0.1700

Data Index: 110253 (C4 (Web Text))

Max Activating Token Index: 907

Text #4

Max Range: 3.6660. Min Range: -3.6660

Max Act: 3.5251. Min Act: -0.1700

Data Index: 701243 (C4 (Web Text))

Max Activating Token Index: 346

Text #5

Max Range: 3.6660. Min Range: -3.6660

Max Act: 3.5094. Min Act: -0.1700

Data Index: 554325 (C4 (Web Text))

Max Activating Token Index: 756

Text #6

Max Range: 3.6660. Min Range: -3.6660

Max Act: 3.5094. Min Act: -0.1700

Data Index: 1293702 (C4 (Web Text))

Max Activating Token Index: 580

Text #7

Max Range: 3.6660. Min Range: -3.6660

Max Act: 3.4781. Min Act: -0.1699

Data Index: 773643 (C4 (Web Text))

Max Activating Token Index: 629

Text #8

Max Range: 3.6660. Min Range: -3.6660

Max Act: 3.4781. Min Act: -0.1700

Data Index: 160991 (C4 (Web Text))

Max Activating Token Index: 571

Text #9

Max Range: 3.6660. Min Range: -3.6660

Max Act: 3.4781. Min Act: -0.1700

Data Index: 544864 (C4 (Web Text))

Max Activating Token Index: 890

Text #10

Max Range: 3.6660. Min Range: -3.6660

Max Act: 3.4624. Min Act: -0.1700

Data Index: 788065 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 3.6660. Min Range: -3.6660

Max Act: 3.4467. Min Act: -0.1700

Data Index: 249045 (C4 (Web Text))

Max Activating Token Index: 68

Text #12

Max Range: 3.6660. Min Range: -3.6660

Max Act: 3.4154. Min Act: -0.1700

Data Index: 1242695 (C4 (Web Text))

Max Activating Token Index: 245

Text #13

Max Range: 3.6660. Min Range: -3.6660

Max Act: 3.4154. Min Act: -0.1699

Data Index: 992136 (C4 (Web Text))

Max Activating Token Index: 439

Text #14

Max Range: 3.6660. Min Range: -3.6660

Max Act: 3.4310. Min Act: -0.1699

Data Index: 519400 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 3.6660. Min Range: -3.6660

Max Act: 3.3997. Min Act: -0.1700

Data Index: 437136 (C4 (Web Text))

Max Activating Token Index: 769

Text #16

Max Range: 3.6660. Min Range: -3.6660

Max Act: 3.3840. Min Act: -0.1700

Data Index: 1171137 (C4 (Web Text))

Max Activating Token Index: 668

Text #17

Max Range: 3.6660. Min Range: -3.6660

Max Act: 3.3997. Min Act: -0.1700

Data Index: 19249 (C4 (Web Text))

Max Activating Token Index: 461

Text #18

Max Range: 3.6660. Min Range: -3.6660

Max Act: 3.4154. Min Act: -0.1700

Data Index: 1213300 (C4 (Web Text))

Max Activating Token Index: 543

Text #19

Max Range: 3.6660. Min Range: -3.6660

Max Act: 3.4154. Min Act: -0.1700

Data Index: 1282010 (C4 (Web Text))

Max Activating Token Index: 653