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

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

Neuron 345 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.4414. Min Range: -3.4414

Max Act: 3.4414. Min Act: -0.1700

Data Index: 624971 (C4 (Web Text))

Max Activating Token Index: 877

Text #1

Max Range: 3.4414. Min Range: -3.4414

Max Act: 3.3316. Min Act: -0.1700

Data Index: 1085304 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 3.4414. Min Range: -3.4414

Max Act: 3.3316. Min Act: -0.1700

Data Index: 721943 (C4 (Web Text))

Max Activating Token Index: 962

Text #3

Max Range: 3.4414. Min Range: -3.4414

Max Act: 3.3159. Min Act: -0.1700

Data Index: 982745 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 3.4414. Min Range: -3.4414

Max Act: 3.3002. Min Act: -0.1700

Data Index: 559426 (C4 (Web Text))

Max Activating Token Index: 454

Text #5

Max Range: 3.4414. Min Range: -3.4414

Max Act: 3.3002. Min Act: -0.1700

Data Index: 828050 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 3.4414. Min Range: -3.4414

Max Act: 3.2688. Min Act: -0.1700

Data Index: 1120226 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 3.4414. Min Range: -3.4414

Max Act: 3.2216. Min Act: -0.1700

Data Index: 1048379 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 3.4414. Min Range: -3.4414

Max Act: 3.2531. Min Act: -0.1700

Data Index: 1268532 (C4 (Web Text))

Max Activating Token Index: 546

Text #9

Max Range: 3.4414. Min Range: -3.4414

Max Act: 3.2374. Min Act: -0.1700

Data Index: 748344 (C4 (Web Text))

Max Activating Token Index: 339

Text #10

Max Range: 3.4414. Min Range: -3.4414

Max Act: 3.2374. Min Act: -0.1700

Data Index: 695197 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 3.4414. Min Range: -3.4414

Max Act: 3.2216. Min Act: -0.1700

Data Index: 994036 (C4 (Web Text))

Max Activating Token Index: 372

Text #12

Max Range: 3.4414. Min Range: -3.4414

Max Act: 3.2059. Min Act: -0.1700

Data Index: 273917 (C4 (Web Text))

Max Activating Token Index: 205

Text #13

Max Range: 3.4414. Min Range: -3.4414

Max Act: 3.2216. Min Act: -0.1700

Data Index: 790847 (C4 (Web Text))

Max Activating Token Index: 97

Text #14

Max Range: 3.4414. Min Range: -3.4414

Max Act: 3.1902. Min Act: -0.1700

Data Index: 156653 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 3.4414. Min Range: -3.4414

Max Act: 3.2059. Min Act: -0.1700

Data Index: 183926 (C4 (Web Text))

Max Activating Token Index: 675

Text #16

Max Range: 3.4414. Min Range: -3.4414

Max Act: 3.2059. Min Act: -0.1700

Data Index: 358378 (C4 (Web Text))

Max Activating Token Index: 369

Text #17

Max Range: 3.4414. Min Range: -3.4414

Max Act: 3.1744. Min Act: -0.1700

Data Index: 463334 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 3.4414. Min Range: -3.4414

Max Act: 3.1744. Min Act: -0.1700

Data Index: 840651 (C4 (Web Text))

Max Activating Token Index: 496

Text #19

Max Range: 3.4414. Min Range: -3.4414

Max Act: 3.1587. Min Act: -0.1700

Data Index: 1256789 (C4 (Web Text))

Max Activating Token Index: 199