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

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

Neuron 1590 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4361. Min Range: -3.4361

Max Act: 3.4361. Min Act: -0.1700

Data Index: 713910 (C4 (Web Text))

Max Activating Token Index: 459

Text #1

Max Range: 3.4361. Min Range: -3.4361

Max Act: 3.3577. Min Act: -0.1700

Data Index: 1015587 (C4 (Web Text))

Max Activating Token Index: 555

Text #2

Max Range: 3.4361. Min Range: -3.4361

Max Act: 3.2321. Min Act: -0.1700

Data Index: 510301 (C4 (Web Text))

Max Activating Token Index: 466

Text #3

Max Range: 3.4361. Min Range: -3.4361

Max Act: 3.2635. Min Act: -0.1700

Data Index: 664892 (C4 (Web Text))

Max Activating Token Index: 487

Text #4

Max Range: 3.4361. Min Range: -3.4361

Max Act: 3.2321. Min Act: -0.1700

Data Index: 272628 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 3.4361. Min Range: -3.4361

Max Act: 3.2163. Min Act: -0.1700

Data Index: 1170576 (C4 (Web Text))

Max Activating Token Index: 768

Text #6

Max Range: 3.4361. Min Range: -3.4361

Max Act: 3.2635. Min Act: -0.1700

Data Index: 237461 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 3.4361. Min Range: -3.4361

Max Act: 3.2163. Min Act: -0.1700

Data Index: 495924 (C4 (Web Text))

Max Activating Token Index: 724

Text #8

Max Range: 3.4361. Min Range: -3.4361

Max Act: 3.2163. Min Act: -0.1700

Data Index: 1129979 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 3.4361. Min Range: -3.4361

Max Act: 3.2478. Min Act: -0.1700

Data Index: 424019 (C4 (Web Text))

Max Activating Token Index: 812

Text #10

Max Range: 3.4361. Min Range: -3.4361

Max Act: 3.2478. Min Act: -0.1700

Data Index: 1327280 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 3.4361. Min Range: -3.4361

Max Act: 3.2635. Min Act: -0.1700

Data Index: 108882 (C4 (Web Text))

Max Activating Token Index: 682

Text #12

Max Range: 3.4361. Min Range: -3.4361

Max Act: 3.2478. Min Act: -0.1700

Data Index: 67661 (C4 (Web Text))

Max Activating Token Index: 978

Text #13

Max Range: 3.4361. Min Range: -3.4361

Max Act: 3.1849. Min Act: -0.1700

Data Index: 616414 (C4 (Web Text))

Max Activating Token Index: 999

Text #14

Max Range: 3.4361. Min Range: -3.4361

Max Act: 3.1849. Min Act: -0.1700

Data Index: 1154505 (C4 (Web Text))

Max Activating Token Index: 729

Text #15

Max Range: 3.4361. Min Range: -3.4361

Max Act: 3.2006. Min Act: -0.1700

Data Index: 502778 (C4 (Web Text))

Max Activating Token Index: 356

Text #16

Max Range: 3.4361. Min Range: -3.4361

Max Act: 3.1849. Min Act: -0.1700

Data Index: 512409 (C4 (Web Text))

Max Activating Token Index: 460

Text #17

Max Range: 3.4361. Min Range: -3.4361

Max Act: 3.1691. Min Act: -0.1700

Data Index: 1141671 (C4 (Web Text))

Max Activating Token Index: 987

Text #18

Max Range: 3.4361. Min Range: -3.4361

Max Act: 3.1849. Min Act: -0.1700

Data Index: 139770 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 3.4361. Min Range: -3.4361

Max Act: 3.1534. Min Act: -0.1700

Data Index: 926112 (C4 (Web Text))

Max Activating Token Index: 138