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

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

Neuron 1685 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: 3.2505. Min Range: -3.2505

Max Act: 3.2505. Min Act: -0.1700

Data Index: 1162769 (C4 (Web Text))

Max Activating Token Index: 393

Text #1

Max Range: 3.2505. Min Range: -3.2505

Max Act: 3.1876. Min Act: -0.1700

Data Index: 819361 (C4 (Web Text))

Max Activating Token Index: 843

Text #2

Max Range: 3.2505. Min Range: -3.2505

Max Act: 3.1719. Min Act: -0.1700

Data Index: 1208141 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 3.2505. Min Range: -3.2505

Max Act: 3.1561. Min Act: -0.1700

Data Index: 836689 (C4 (Web Text))

Max Activating Token Index: 370

Text #4

Max Range: 3.2505. Min Range: -3.2505

Max Act: 3.1246. Min Act: -0.1700

Data Index: 106788 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 3.2505. Min Range: -3.2505

Max Act: 3.1561. Min Act: -0.1700

Data Index: 174076 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 3.2505. Min Range: -3.2505

Max Act: 3.1404. Min Act: -0.1700

Data Index: 91658 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 3.2505. Min Range: -3.2505

Max Act: 3.1246. Min Act: -0.1700

Data Index: 545569 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 3.2505. Min Range: -3.2505

Max Act: 3.0773. Min Act: -0.1700

Data Index: 467 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 3.2505. Min Range: -3.2505

Max Act: 3.0931. Min Act: -0.1700

Data Index: 649993 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 3.2505. Min Range: -3.2505

Max Act: 3.0773. Min Act: -0.1700

Data Index: 54227 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 3.2505. Min Range: -3.2505

Max Act: 3.0616. Min Act: -0.1700

Data Index: 213141 (C4 (Web Text))

Max Activating Token Index: 499

Text #12

Max Range: 3.2505. Min Range: -3.2505

Max Act: 3.0616. Min Act: -0.1700

Data Index: 425374 (C4 (Web Text))

Max Activating Token Index: 948

Text #13

Max Range: 3.2505. Min Range: -3.2505

Max Act: 3.0458. Min Act: -0.1700

Data Index: 6526 (C4 (Web Text))

Max Activating Token Index: 746

Text #14

Max Range: 3.2505. Min Range: -3.2505

Max Act: 3.0300. Min Act: -0.1700

Data Index: 118506 (C4 (Web Text))

Max Activating Token Index: 184

Text #15

Max Range: 3.2505. Min Range: -3.2505

Max Act: 3.0458. Min Act: -0.1700

Data Index: 548397 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 3.2505. Min Range: -3.2505

Max Act: 3.0458. Min Act: -0.1700

Data Index: 969998 (C4 (Web Text))

Max Activating Token Index: 665

Text #17

Max Range: 3.2505. Min Range: -3.2505

Max Act: 3.0458. Min Act: -0.1700

Data Index: 837314 (C4 (Web Text))

Max Activating Token Index: 19

Text #18

Max Range: 3.2505. Min Range: -3.2505

Max Act: 3.0300. Min Act: -0.1700

Data Index: 15356 (C4 (Web Text))

Max Activating Token Index: 168

Text #19

Max Range: 3.2505. Min Range: -3.2505

Max Act: 3.0300. Min Act: -0.1700

Data Index: 381845 (C4 (Web Text))

Max Activating Token Index: 311