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

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

Neuron 371 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: 5.5482. Min Range: -5.5482

Max Act: 5.5482. Min Act: -0.1700

Data Index: 219031 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 5.5482. Min Range: -5.5482

Max Act: 5.3920. Min Act: -0.1700

Data Index: 590370 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 5.5482. Min Range: -5.5482

Max Act: 5.3295. Min Act: -0.1700

Data Index: 192420 (C4 (Web Text))

Max Activating Token Index: 763

Text #3

Max Range: 5.5482. Min Range: -5.5482

Max Act: 5.2982. Min Act: -0.1700

Data Index: 393979 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 5.5482. Min Range: -5.5482

Max Act: 5.2982. Min Act: -0.1700

Data Index: 346760 (C4 (Web Text))

Max Activating Token Index: 535

Text #5

Max Range: 5.5482. Min Range: -5.5482

Max Act: 5.2982. Min Act: -0.1700

Data Index: 545654 (C4 (Web Text))

Max Activating Token Index: 424

Text #6

Max Range: 5.5482. Min Range: -5.5482

Max Act: 5.3295. Min Act: -0.1700

Data Index: 406450 (C4 (Web Text))

Max Activating Token Index: 833

Text #7

Max Range: 5.5482. Min Range: -5.5482

Max Act: 5.2982. Min Act: -0.1700

Data Index: 872164 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 5.5482. Min Range: -5.5482

Max Act: 5.2357. Min Act: -0.1700

Data Index: 247623 (C4 (Web Text))

Max Activating Token Index: 827

Text #9

Max Range: 5.5482. Min Range: -5.5482

Max Act: 5.2045. Min Act: -0.1700

Data Index: 859044 (C4 (Web Text))

Max Activating Token Index: 784

Text #10

Max Range: 5.5482. Min Range: -5.5482

Max Act: 5.2357. Min Act: -0.1700

Data Index: 549854 (C4 (Web Text))

Max Activating Token Index: 522

Text #11

Max Range: 5.5482. Min Range: -5.5482

Max Act: 5.2045. Min Act: -0.1700

Data Index: 196966 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 5.5482. Min Range: -5.5482

Max Act: 5.3295. Min Act: -0.1700

Data Index: 331988 (C4 (Web Text))

Max Activating Token Index: 583

Text #13

Max Range: 5.5482. Min Range: -5.5482

Max Act: 5.2357. Min Act: -0.1700

Data Index: 994684 (C4 (Web Text))

Max Activating Token Index: 634

Text #14

Max Range: 5.5482. Min Range: -5.5482

Max Act: 5.2357. Min Act: -0.1700

Data Index: 917288 (C4 (Web Text))

Max Activating Token Index: 607

Text #15

Max Range: 5.5482. Min Range: -5.5482

Max Act: 5.2045. Min Act: -0.1700

Data Index: 628883 (C4 (Web Text))

Max Activating Token Index: 684

Text #16

Max Range: 5.5482. Min Range: -5.5482

Max Act: 5.2045. Min Act: -0.1700

Data Index: 343131 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 5.5482. Min Range: -5.5482

Max Act: 5.1732. Min Act: -0.1700

Data Index: 587524 (C4 (Web Text))

Max Activating Token Index: 895

Text #18

Max Range: 5.5482. Min Range: -5.5482

Max Act: 5.2045. Min Act: -0.1700

Data Index: 368030 (C4 (Web Text))

Max Activating Token Index: 125

Text #19

Max Range: 5.5482. Min Range: -5.5482

Max Act: 5.1732. Min Act: -0.1700

Data Index: 823006 (C4 (Web Text))

Max Activating Token Index: 493