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

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

Neuron 1862 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.3346. Min Range: -3.3346

Max Act: 3.3346. Min Act: -0.1700

Data Index: 975563 (C4 (Web Text))

Max Activating Token Index: 478

Text #1

Max Range: 3.3346. Min Range: -3.3346

Max Act: 3.3346. Min Act: -0.1700

Data Index: 1125653 (C4 (Web Text))

Max Activating Token Index: 616

Text #2

Max Range: 3.3346. Min Range: -3.3346

Max Act: 3.3032. Min Act: -0.1700

Data Index: 672068 (C4 (Web Text))

Max Activating Token Index: 454

Text #3

Max Range: 3.3346. Min Range: -3.3346

Max Act: 3.3032. Min Act: -0.1700

Data Index: 1256616 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 3.3346. Min Range: -3.3346

Max Act: 3.3032. Min Act: -0.1700

Data Index: 976809 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 3.3346. Min Range: -3.3346

Max Act: 3.3032. Min Act: -0.1700

Data Index: 1155036 (C4 (Web Text))

Max Activating Token Index: 849

Text #6

Max Range: 3.3346. Min Range: -3.3346

Max Act: 3.2560. Min Act: -0.1700

Data Index: 63392 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 3.3346. Min Range: -3.3346

Max Act: 3.2560. Min Act: -0.1700

Data Index: 370448 (C4 (Web Text))

Max Activating Token Index: 368

Text #8

Max Range: 3.3346. Min Range: -3.3346

Max Act: 3.2717. Min Act: -0.1700

Data Index: 940319 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 3.3346. Min Range: -3.3346

Max Act: 3.2717. Min Act: -0.1700

Data Index: 853849 (C4 (Web Text))

Max Activating Token Index: 362

Text #10

Max Range: 3.3346. Min Range: -3.3346

Max Act: 3.2403. Min Act: -0.1700

Data Index: 233339 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 3.3346. Min Range: -3.3346

Max Act: 3.2560. Min Act: -0.1700

Data Index: 1184527 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 3.3346. Min Range: -3.3346

Max Act: 3.2089. Min Act: -0.1700

Data Index: 595460 (C4 (Web Text))

Max Activating Token Index: 1008

Text #13

Max Range: 3.3346. Min Range: -3.3346

Max Act: 3.2246. Min Act: -0.1700

Data Index: 1310124 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 3.3346. Min Range: -3.3346

Max Act: 3.2246. Min Act: -0.1700

Data Index: 665314 (C4 (Web Text))

Max Activating Token Index: 794

Text #15

Max Range: 3.3346. Min Range: -3.3346

Max Act: 3.2403. Min Act: -0.1700

Data Index: 1326758 (C4 (Web Text))

Max Activating Token Index: 432

Text #16

Max Range: 3.3346. Min Range: -3.3346

Max Act: 3.2089. Min Act: -0.1700

Data Index: 963176 (C4 (Web Text))

Max Activating Token Index: 480

Text #17

Max Range: 3.3346. Min Range: -3.3346

Max Act: 3.2089. Min Act: -0.1700

Data Index: 185676 (C4 (Web Text))

Max Activating Token Index: 348

Text #18

Max Range: 3.3346. Min Range: -3.3346

Max Act: 3.2246. Min Act: -0.1700

Data Index: 633514 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 3.3346. Min Range: -3.3346

Max Act: 3.2246. Min Act: -0.1700

Data Index: 413829 (C4 (Web Text))

Max Activating Token Index: 124