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

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

Neuron 85 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: 5.0577. Min Range: -5.0577

Max Act: 5.0264. Min Act: -0.1700

Data Index: 820008 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 5.0577. Min Range: -5.0577

Max Act: 5.0577. Min Act: -0.1700

Data Index: 157702 (C4 (Web Text))

Max Activating Token Index: 415

Text #2

Max Range: 5.0577. Min Range: -5.0577

Max Act: 5.0577. Min Act: -0.1700

Data Index: 1137004 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 5.0577. Min Range: -5.0577

Max Act: 5.0264. Min Act: -0.1700

Data Index: 1170760 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 5.0577. Min Range: -5.0577

Max Act: 5.0264. Min Act: -0.1700

Data Index: 585799 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 5.0577. Min Range: -5.0577

Max Act: 5.0264. Min Act: -0.1700

Data Index: 100386 (C4 (Web Text))

Max Activating Token Index: 360

Text #6

Max Range: 5.0577. Min Range: -5.0577

Max Act: 5.0264. Min Act: -0.1700

Data Index: 567471 (C4 (Web Text))

Max Activating Token Index: 491

Text #7

Max Range: 5.0577. Min Range: -5.0577

Max Act: 5.0264. Min Act: -0.1700

Data Index: 1326679 (C4 (Web Text))

Max Activating Token Index: 565

Text #8

Max Range: 5.0577. Min Range: -5.0577

Max Act: 5.0264. Min Act: -0.1700

Data Index: 78545 (C4 (Web Text))

Max Activating Token Index: 355

Text #9

Max Range: 5.0577. Min Range: -5.0577

Max Act: 5.0264. Min Act: -0.1700

Data Index: 197300 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 5.0577. Min Range: -5.0577

Max Act: 5.0264. Min Act: -0.1700

Data Index: 1109559 (C4 (Web Text))

Max Activating Token Index: 474

Text #11

Max Range: 5.0577. Min Range: -5.0577

Max Act: 5.0264. Min Act: -0.1700

Data Index: 503061 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 5.0577. Min Range: -5.0577

Max Act: 4.9952. Min Act: -0.1700

Data Index: 21145 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 5.0577. Min Range: -5.0577

Max Act: 4.9952. Min Act: -0.1700

Data Index: 965158 (C4 (Web Text))

Max Activating Token Index: 662

Text #14

Max Range: 5.0577. Min Range: -5.0577

Max Act: 4.9952. Min Act: -0.1700

Data Index: 469485 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 5.0577. Min Range: -5.0577

Max Act: 4.9639. Min Act: -0.1700

Data Index: 676028 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 5.0577. Min Range: -5.0577

Max Act: 4.9952. Min Act: -0.1700

Data Index: 653559 (C4 (Web Text))

Max Activating Token Index: 387

Text #17

Max Range: 5.0577. Min Range: -5.0577

Max Act: 4.9327. Min Act: -0.1700

Data Index: 243209 (C4 (Web Text))

Max Activating Token Index: 575

Text #18

Max Range: 5.0577. Min Range: -5.0577

Max Act: 4.9639. Min Act: -0.1700

Data Index: 4023 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 5.0577. Min Range: -5.0577

Max Act: 4.9639. Min Act: -0.1700

Data Index: 225260 (C4 (Web Text))

Max Activating Token Index: 529