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

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

Neuron 470 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: 5.1209. Min Range: -5.1209

Max Act: 5.1209. Min Act: -0.1700

Data Index: 49396 (C4 (Web Text))

Max Activating Token Index: 644

Text #1

Max Range: 5.1209. Min Range: -5.1209

Max Act: 5.1209. Min Act: -0.1700

Data Index: 1099857 (C4 (Web Text))

Max Activating Token Index: 412

Text #2

Max Range: 5.1209. Min Range: -5.1209

Max Act: 5.1209. Min Act: -0.1700

Data Index: 593184 (C4 (Web Text))

Max Activating Token Index: 622

Text #3

Max Range: 5.1209. Min Range: -5.1209

Max Act: 5.0897. Min Act: -0.1700

Data Index: 711046 (C4 (Web Text))

Max Activating Token Index: 557

Text #4

Max Range: 5.1209. Min Range: -5.1209

Max Act: 5.0897. Min Act: -0.1700

Data Index: 1063265 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 5.1209. Min Range: -5.1209

Max Act: 5.0897. Min Act: -0.1700

Data Index: 1210964 (C4 (Web Text))

Max Activating Token Index: 349

Text #6

Max Range: 5.1209. Min Range: -5.1209

Max Act: 5.0897. Min Act: -0.1700

Data Index: 1138946 (C4 (Web Text))

Max Activating Token Index: 535

Text #7

Max Range: 5.1209. Min Range: -5.1209

Max Act: 5.0897. Min Act: -0.1700

Data Index: 1034893 (C4 (Web Text))

Max Activating Token Index: 645

Text #8

Max Range: 5.1209. Min Range: -5.1209

Max Act: 5.0584. Min Act: -0.1700

Data Index: 522151 (C4 (Web Text))

Max Activating Token Index: 764

Text #9

Max Range: 5.1209. Min Range: -5.1209

Max Act: 5.0897. Min Act: -0.1700

Data Index: 1329320 (C4 (Web Text))

Max Activating Token Index: 595

Text #10

Max Range: 5.1209. Min Range: -5.1209

Max Act: 5.0897. Min Act: -0.1700

Data Index: 1029475 (C4 (Web Text))

Max Activating Token Index: 657

Text #11

Max Range: 5.1209. Min Range: -5.1209

Max Act: 5.0584. Min Act: -0.1700

Data Index: 3323 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 5.1209. Min Range: -5.1209

Max Act: 5.0584. Min Act: -0.1700

Data Index: 830713 (C4 (Web Text))

Max Activating Token Index: 708

Text #13

Max Range: 5.1209. Min Range: -5.1209

Max Act: 5.0272. Min Act: -0.1700

Data Index: 823678 (C4 (Web Text))

Max Activating Token Index: 264

Text #14

Max Range: 5.1209. Min Range: -5.1209

Max Act: 5.0584. Min Act: -0.1700

Data Index: 762734 (C4 (Web Text))

Max Activating Token Index: 388

Text #15

Max Range: 5.1209. Min Range: -5.1209

Max Act: 5.0584. Min Act: -0.1700

Data Index: 874434 (C4 (Web Text))

Max Activating Token Index: 888

Text #16

Max Range: 5.1209. Min Range: -5.1209

Max Act: 5.0584. Min Act: -0.1700

Data Index: 1084239 (C4 (Web Text))

Max Activating Token Index: 263

Text #17

Max Range: 5.1209. Min Range: -5.1209

Max Act: 5.0584. Min Act: -0.1700

Data Index: 914837 (C4 (Web Text))

Max Activating Token Index: 586

Text #18

Max Range: 5.1209. Min Range: -5.1209

Max Act: 5.0584. Min Act: -0.1699

Data Index: 256383 (C4 (Web Text))

Max Activating Token Index: 516

Text #19

Max Range: 5.1209. Min Range: -5.1209

Max Act: 5.0584. Min Act: -0.1700

Data Index: 94606 (C4 (Web Text))

Max Activating Token Index: 688