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

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

Neuron 112 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6996. Min Range: -5.6996

Max Act: 5.6996. Min Act: -0.1700

Data Index: 364477 (C4 (Web Text))

Max Activating Token Index: 584

Text #1

Max Range: 5.6996. Min Range: -5.6996

Max Act: 5.6839. Min Act: -0.1700

Data Index: 1022806 (C4 (Web Text))

Max Activating Token Index: 539

Text #2

Max Range: 5.6996. Min Range: -5.6996

Max Act: 5.5902. Min Act: -0.1700

Data Index: 235505 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 5.6996. Min Range: -5.6996

Max Act: 5.5902. Min Act: -0.1700

Data Index: 253817 (C4 (Web Text))

Max Activating Token Index: 829

Text #4

Max Range: 5.6996. Min Range: -5.6996

Max Act: 5.5589. Min Act: -0.1700

Data Index: 377995 (C4 (Web Text))

Max Activating Token Index: 615

Text #5

Max Range: 5.6996. Min Range: -5.6996

Max Act: 5.6214. Min Act: -0.1700

Data Index: 65030 (C4 (Web Text))

Max Activating Token Index: 557

Text #6

Max Range: 5.6996. Min Range: -5.6996

Max Act: 5.5433. Min Act: -0.1700

Data Index: 904699 (C4 (Web Text))

Max Activating Token Index: 413

Text #7

Max Range: 5.6996. Min Range: -5.6996

Max Act: 5.5433. Min Act: -0.1700

Data Index: 1122264 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 5.6996. Min Range: -5.6996

Max Act: 5.5277. Min Act: -0.1700

Data Index: 497256 (C4 (Web Text))

Max Activating Token Index: 195

Text #9

Max Range: 5.6996. Min Range: -5.6996

Max Act: 5.5746. Min Act: -0.1700

Data Index: 229755 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 5.6996. Min Range: -5.6996

Max Act: 5.5433. Min Act: -0.1700

Data Index: 621668 (C4 (Web Text))

Max Activating Token Index: 442

Text #11

Max Range: 5.6996. Min Range: -5.6996

Max Act: 5.4964. Min Act: -0.1700

Data Index: 734705 (C4 (Web Text))

Max Activating Token Index: 841

Text #12

Max Range: 5.6996. Min Range: -5.6996

Max Act: 5.5277. Min Act: -0.1700

Data Index: 364228 (C4 (Web Text))

Max Activating Token Index: 332

Text #13

Max Range: 5.6996. Min Range: -5.6996

Max Act: 5.5121. Min Act: -0.1700

Data Index: 789588 (C4 (Web Text))

Max Activating Token Index: 545

Text #14

Max Range: 5.6996. Min Range: -5.6996

Max Act: 5.4496. Min Act: -0.1700

Data Index: 492125 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 5.6996. Min Range: -5.6996

Max Act: 5.4964. Min Act: -0.1700

Data Index: 894829 (C4 (Web Text))

Max Activating Token Index: 531

Text #16

Max Range: 5.6996. Min Range: -5.6996

Max Act: 5.5121. Min Act: -0.1700

Data Index: 495637 (C4 (Web Text))

Max Activating Token Index: 597

Text #17

Max Range: 5.6996. Min Range: -5.6996

Max Act: 5.5277. Min Act: -0.1700

Data Index: 307928 (C4 (Web Text))

Max Activating Token Index: 461

Text #18

Max Range: 5.6996. Min Range: -5.6996

Max Act: 5.5277. Min Act: -0.1700

Data Index: 1041773 (C4 (Web Text))

Max Activating Token Index: 805

Text #19

Max Range: 5.6996. Min Range: -5.6996

Max Act: 5.4652. Min Act: -0.1700

Data Index: 388210 (C4 (Web Text))

Max Activating Token Index: 715