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

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

Neuron 1042 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: 5.2269. Min Range: -5.2269

Max Act: 5.1956. Min Act: -0.1700

Data Index: 768225 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 5.2269. Min Range: -5.2269

Max Act: 5.2269. Min Act: -0.1700

Data Index: 976554 (C4 (Web Text))

Max Activating Token Index: 334

Text #2

Max Range: 5.2269. Min Range: -5.2269

Max Act: 5.2269. Min Act: -0.1700

Data Index: 1767 (C4 (Web Text))

Max Activating Token Index: 187

Text #3

Max Range: 5.2269. Min Range: -5.2269

Max Act: 5.1019. Min Act: -0.1700

Data Index: 484399 (C4 (Web Text))

Max Activating Token Index: 467

Text #4

Max Range: 5.2269. Min Range: -5.2269

Max Act: 5.1644. Min Act: -0.1700

Data Index: 1049007 (C4 (Web Text))

Max Activating Token Index: 294

Text #5

Max Range: 5.2269. Min Range: -5.2269

Max Act: 5.2269. Min Act: -0.1700

Data Index: 782471 (C4 (Web Text))

Max Activating Token Index: 690

Text #6

Max Range: 5.2269. Min Range: -5.2269

Max Act: 5.0394. Min Act: -0.1700

Data Index: 848445 (C4 (Web Text))

Max Activating Token Index: 371

Text #7

Max Range: 5.2269. Min Range: -5.2269

Max Act: 5.0081. Min Act: -0.1700

Data Index: 684002 (C4 (Web Text))

Max Activating Token Index: 514

Text #8

Max Range: 5.2269. Min Range: -5.2269

Max Act: 5.1644. Min Act: -0.1700

Data Index: 133735 (C4 (Web Text))

Max Activating Token Index: 256

Text #9

Max Range: 5.2269. Min Range: -5.2269

Max Act: 5.0394. Min Act: -0.1700

Data Index: 1201144 (C4 (Web Text))

Max Activating Token Index: 226

Text #10

Max Range: 5.2269. Min Range: -5.2269

Max Act: 5.0706. Min Act: -0.1700

Data Index: 992589 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 5.2269. Min Range: -5.2269

Max Act: 4.9769. Min Act: -0.1700

Data Index: 155737 (C4 (Web Text))

Max Activating Token Index: 402

Text #12

Max Range: 5.2269. Min Range: -5.2269

Max Act: 5.0081. Min Act: -0.1700

Data Index: 617895 (C4 (Web Text))

Max Activating Token Index: 184

Text #13

Max Range: 5.2269. Min Range: -5.2269

Max Act: 5.1331. Min Act: -0.1700

Data Index: 412113 (C4 (Web Text))

Max Activating Token Index: 434

Text #14

Max Range: 5.2269. Min Range: -5.2269

Max Act: 4.9769. Min Act: -0.1700

Data Index: 357766 (C4 (Web Text))

Max Activating Token Index: 251

Text #15

Max Range: 5.2269. Min Range: -5.2269

Max Act: 5.0706. Min Act: -0.1700

Data Index: 526470 (C4 (Web Text))

Max Activating Token Index: 154

Text #16

Max Range: 5.2269. Min Range: -5.2269

Max Act: 5.0394. Min Act: -0.1700

Data Index: 1200803 (C4 (Web Text))

Max Activating Token Index: 209

Text #17

Max Range: 5.2269. Min Range: -5.2269

Max Act: 5.0081. Min Act: -0.1700

Data Index: 54990 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 5.2269. Min Range: -5.2269

Max Act: 5.0081. Min Act: -0.1700

Data Index: 526865 (C4 (Web Text))

Max Activating Token Index: 125

Text #19

Max Range: 5.2269. Min Range: -5.2269

Max Act: 5.0081. Min Act: -0.1700

Data Index: 992059 (C4 (Web Text))

Max Activating Token Index: 290