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

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

Neuron 763 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: 3.7804. Min Range: -3.7804

Max Act: 3.7804. Min Act: -0.1700

Data Index: 999500 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 3.7804. Min Range: -3.7804

Max Act: 3.6866. Min Act: -0.1700

Data Index: 1086755 (C4 (Web Text))

Max Activating Token Index: 567

Text #2

Max Range: 3.7804. Min Range: -3.7804

Max Act: 3.6553. Min Act: -0.1700

Data Index: 1105091 (C4 (Web Text))

Max Activating Token Index: 399

Text #3

Max Range: 3.7804. Min Range: -3.7804

Max Act: 3.6553. Min Act: -0.1700

Data Index: 1083277 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 3.7804. Min Range: -3.7804

Max Act: 3.6240. Min Act: -0.1700

Data Index: 790979 (C4 (Web Text))

Max Activating Token Index: 696

Text #5

Max Range: 3.7804. Min Range: -3.7804

Max Act: 3.5613. Min Act: -0.1700

Data Index: 100008 (C4 (Web Text))

Max Activating Token Index: 535

Text #6

Max Range: 3.7804. Min Range: -3.7804

Max Act: 3.6240. Min Act: -0.1700

Data Index: 945745 (C4 (Web Text))

Max Activating Token Index: 316

Text #7

Max Range: 3.7804. Min Range: -3.7804

Max Act: 3.5300. Min Act: -0.1700

Data Index: 407625 (C4 (Web Text))

Max Activating Token Index: 115

Text #8

Max Range: 3.7804. Min Range: -3.7804

Max Act: 3.5613. Min Act: -0.1700

Data Index: 982438 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 3.7804. Min Range: -3.7804

Max Act: 3.5613. Min Act: -0.1700

Data Index: 1233192 (C4 (Web Text))

Max Activating Token Index: 678

Text #10

Max Range: 3.7804. Min Range: -3.7804

Max Act: 3.6240. Min Act: -0.1700

Data Index: 1238342 (C4 (Web Text))

Max Activating Token Index: 850

Text #11

Max Range: 3.7804. Min Range: -3.7804

Max Act: 3.5613. Min Act: -0.1700

Data Index: 507449 (C4 (Web Text))

Max Activating Token Index: 280

Text #12

Max Range: 3.7804. Min Range: -3.7804

Max Act: 3.5300. Min Act: -0.1700

Data Index: 584100 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 3.7804. Min Range: -3.7804

Max Act: 3.5613. Min Act: -0.1700

Data Index: 971253 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 3.7804. Min Range: -3.7804

Max Act: 3.5613. Min Act: -0.1700

Data Index: 1071659 (C4 (Web Text))

Max Activating Token Index: 542

Text #15

Max Range: 3.7804. Min Range: -3.7804

Max Act: 3.5926. Min Act: -0.1700

Data Index: 368153 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 3.7804. Min Range: -3.7804

Max Act: 3.5613. Min Act: -0.1700

Data Index: 382092 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 3.7804. Min Range: -3.7804

Max Act: 3.5613. Min Act: -0.1700

Data Index: 1136439 (C4 (Web Text))

Max Activating Token Index: 487

Text #18

Max Range: 3.7804. Min Range: -3.7804

Max Act: 3.4987. Min Act: -0.1700

Data Index: 688469 (C4 (Web Text))

Max Activating Token Index: 416

Text #19

Max Range: 3.7804. Min Range: -3.7804

Max Act: 3.5300. Min Act: -0.1700

Data Index: 130425 (C4 (Web Text))

Max Activating Token Index: 555