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

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

Neuron 43 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: 3.5531. Min Range: -3.5531

Max Act: 3.5374. Min Act: -0.1700

Data Index: 22099 (C4 (Web Text))

Max Activating Token Index: 633

Text #1

Max Range: 3.5531. Min Range: -3.5531

Max Act: 3.5374. Min Act: -0.1700

Data Index: 1038724 (C4 (Web Text))

Max Activating Token Index: 734

Text #2

Max Range: 3.5531. Min Range: -3.5531

Max Act: 3.5531. Min Act: -0.1700

Data Index: 725776 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 3.5531. Min Range: -3.5531

Max Act: 3.5061. Min Act: -0.1700

Data Index: 582700 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 3.5531. Min Range: -3.5531

Max Act: 3.4747. Min Act: -0.1700

Data Index: 429218 (C4 (Web Text))

Max Activating Token Index: 1007

Text #5

Max Range: 3.5531. Min Range: -3.5531

Max Act: 3.5061. Min Act: -0.1700

Data Index: 1056972 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 3.5531. Min Range: -3.5531

Max Act: 3.4590. Min Act: -0.1700

Data Index: 999892 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 3.5531. Min Range: -3.5531

Max Act: 3.5061. Min Act: -0.1700

Data Index: 990641 (C4 (Web Text))

Max Activating Token Index: 736

Text #8

Max Range: 3.5531. Min Range: -3.5531

Max Act: 3.4590. Min Act: -0.1700

Data Index: 558979 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 3.5531. Min Range: -3.5531

Max Act: 3.3963. Min Act: -0.1700

Data Index: 966463 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 3.5531. Min Range: -3.5531

Max Act: 3.4434. Min Act: -0.1700

Data Index: 739 (C4 (Web Text))

Max Activating Token Index: 843

Text #11

Max Range: 3.5531. Min Range: -3.5531

Max Act: 3.3963. Min Act: -0.1700

Data Index: 310331 (C4 (Web Text))

Max Activating Token Index: 207

Text #12

Max Range: 3.5531. Min Range: -3.5531

Max Act: 3.4434. Min Act: -0.1700

Data Index: 970894 (C4 (Web Text))

Max Activating Token Index: 983

Text #13

Max Range: 3.5531. Min Range: -3.5531

Max Act: 3.3493. Min Act: -0.1700

Data Index: 563817 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 3.5531. Min Range: -3.5531

Max Act: 3.3963. Min Act: -0.1700

Data Index: 384250 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 3.5531. Min Range: -3.5531

Max Act: 3.3649. Min Act: -0.1700

Data Index: 300509 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 3.5531. Min Range: -3.5531

Max Act: 3.4434. Min Act: -0.1700

Data Index: 1308178 (C4 (Web Text))

Max Activating Token Index: 471

Text #17

Max Range: 3.5531. Min Range: -3.5531

Max Act: 3.4434. Min Act: -0.1700

Data Index: 199850 (C4 (Web Text))

Max Activating Token Index: 298

Text #18

Max Range: 3.5531. Min Range: -3.5531

Max Act: 3.3963. Min Act: -0.1700

Data Index: 509335 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 3.5531. Min Range: -3.5531

Max Act: 3.3022. Min Act: -0.1700

Data Index: 541346 (C4 (Web Text))

Max Activating Token Index: 435