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

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

Neuron 343 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: 3.5342. Min Range: -3.5342

Max Act: 3.5342. Min Act: -0.1700

Data Index: 881818 (C4 (Web Text))

Max Activating Token Index: 651

Text #1

Max Range: 3.5342. Min Range: -3.5342

Max Act: 3.4402. Min Act: -0.1700

Data Index: 210894 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 3.5342. Min Range: -3.5342

Max Act: 3.4245. Min Act: -0.1700

Data Index: 608938 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 3.5342. Min Range: -3.5342

Max Act: 3.3774. Min Act: -0.1700

Data Index: 1511495 (Python Code)

Max Activating Token Index: 712

Text #4

Max Range: 3.5342. Min Range: -3.5342

Max Act: 3.4088. Min Act: -0.1700

Data Index: 479750 (C4 (Web Text))

Max Activating Token Index: 870

Text #5

Max Range: 3.5342. Min Range: -3.5342

Max Act: 3.3931. Min Act: -0.1700

Data Index: 866585 (C4 (Web Text))

Max Activating Token Index: 616

Text #6

Max Range: 3.5342. Min Range: -3.5342

Max Act: 3.3303. Min Act: -0.1700

Data Index: 710211 (C4 (Web Text))

Max Activating Token Index: 654

Text #7

Max Range: 3.5342. Min Range: -3.5342

Max Act: 3.3460. Min Act: -0.1700

Data Index: 1457436 (Python Code)

Max Activating Token Index: 768

Text #8

Max Range: 3.5342. Min Range: -3.5342

Max Act: 3.3460. Min Act: -0.1700

Data Index: 1535115 (Python Code)

Max Activating Token Index: 631

Text #9

Max Range: 3.5342. Min Range: -3.5342

Max Act: 3.3460. Min Act: -0.1700

Data Index: 1250796 (C4 (Web Text))

Max Activating Token Index: 582

Text #10

Max Range: 3.5342. Min Range: -3.5342

Max Act: 3.3303. Min Act: -0.1700

Data Index: 1601793 (Python Code)

Max Activating Token Index: 388

Text #11

Max Range: 3.5342. Min Range: -3.5342

Max Act: 3.3146. Min Act: -0.1700

Data Index: 1613161 (Python Code)

Max Activating Token Index: 739

Text #12

Max Range: 3.5342. Min Range: -3.5342

Max Act: 3.2989. Min Act: -0.1700

Data Index: 179327 (C4 (Web Text))

Max Activating Token Index: 805

Text #13

Max Range: 3.5342. Min Range: -3.5342

Max Act: 3.3146. Min Act: -0.1700

Data Index: 1621766 (Python Code)

Max Activating Token Index: 252

Text #14

Max Range: 3.5342. Min Range: -3.5342

Max Act: 3.3146. Min Act: -0.1700

Data Index: 1157264 (C4 (Web Text))

Max Activating Token Index: 454

Text #15

Max Range: 3.5342. Min Range: -3.5342

Max Act: 3.2832. Min Act: -0.1700

Data Index: 393874 (C4 (Web Text))

Max Activating Token Index: 852

Text #16

Max Range: 3.5342. Min Range: -3.5342

Max Act: 3.2832. Min Act: -0.1700

Data Index: 264081 (C4 (Web Text))

Max Activating Token Index: 253

Text #17

Max Range: 3.5342. Min Range: -3.5342

Max Act: 3.2832. Min Act: -0.1700

Data Index: 1203001 (C4 (Web Text))

Max Activating Token Index: 169

Text #18

Max Range: 3.5342. Min Range: -3.5342

Max Act: 3.2832. Min Act: -0.1700

Data Index: 21352 (C4 (Web Text))

Max Activating Token Index: 667

Text #19

Max Range: 3.5342. Min Range: -3.5342

Max Act: 3.2361. Min Act: -0.1700

Data Index: 547919 (C4 (Web Text))

Max Activating Token Index: 79