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

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

Neuron 1405 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2419. Min Range: -3.2419

Max Act: 3.2419. Min Act: -0.1700

Data Index: 1062518 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 3.2419. Min Range: -3.2419

Max Act: 3.1317. Min Act: -0.1700

Data Index: 704009 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 3.2419. Min Range: -3.2419

Max Act: 3.1317. Min Act: -0.1700

Data Index: 383398 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 3.2419. Min Range: -3.2419

Max Act: 3.1317. Min Act: -0.1700

Data Index: 1603162 (Python Code)

Max Activating Token Index: 198

Text #4

Max Range: 3.2419. Min Range: -3.2419

Max Act: 3.0844. Min Act: -0.1700

Data Index: 504932 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 3.2419. Min Range: -3.2419

Max Act: 3.0844. Min Act: -0.1700

Data Index: 453528 (C4 (Web Text))

Max Activating Token Index: 473

Text #6

Max Range: 3.2419. Min Range: -3.2419

Max Act: 3.0686. Min Act: -0.1700

Data Index: 433358 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 3.2419. Min Range: -3.2419

Max Act: 3.0213. Min Act: -0.1700

Data Index: 875664 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 3.2419. Min Range: -3.2419

Max Act: 3.0371. Min Act: -0.1700

Data Index: 692725 (C4 (Web Text))

Max Activating Token Index: 6

Text #9

Max Range: 3.2419. Min Range: -3.2419

Max Act: 3.0213. Min Act: -0.1700

Data Index: 1216232 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 3.2419. Min Range: -3.2419

Max Act: 3.0213. Min Act: -0.1700

Data Index: 361167 (C4 (Web Text))

Max Activating Token Index: 3

Text #11

Max Range: 3.2419. Min Range: -3.2419

Max Act: 2.9896. Min Act: -0.1700

Data Index: 516605 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 3.2419. Min Range: -3.2419

Max Act: 2.9738. Min Act: -0.1700

Data Index: 1092802 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 3.2419. Min Range: -3.2419

Max Act: 2.9738. Min Act: -0.1700

Data Index: 1324019 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 3.2419. Min Range: -3.2419

Max Act: 2.9580. Min Act: -0.1700

Data Index: 579180 (C4 (Web Text))

Max Activating Token Index: 44

Text #15

Max Range: 3.2419. Min Range: -3.2419

Max Act: 2.9105. Min Act: -0.1700

Data Index: 336511 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 3.2419. Min Range: -3.2419

Max Act: 2.9263. Min Act: -0.1700

Data Index: 124999 (C4 (Web Text))

Max Activating Token Index: 25

Text #17

Max Range: 3.2419. Min Range: -3.2419

Max Act: 2.9263. Min Act: -0.1700

Data Index: 689663 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 3.2419. Min Range: -3.2419

Max Act: 2.9105. Min Act: -0.1700

Data Index: 1219312 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 3.2419. Min Range: -3.2419

Max Act: 2.9105. Min Act: -0.1700

Data Index: 1215624 (C4 (Web Text))

Max Activating Token Index: 470