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

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

Neuron 292 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: 3.8556. Min Range: -3.8556

Max Act: 3.8556. Min Act: -0.1700

Data Index: 264351 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 3.8556. Min Range: -3.8556

Max Act: 3.7305. Min Act: -0.1700

Data Index: 742317 (C4 (Web Text))

Max Activating Token Index: 647

Text #2

Max Range: 3.8556. Min Range: -3.8556

Max Act: 3.7305. Min Act: -0.1700

Data Index: 1246474 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 3.8556. Min Range: -3.8556

Max Act: 3.7618. Min Act: -0.1700

Data Index: 1128951 (C4 (Web Text))

Max Activating Token Index: 625

Text #4

Max Range: 3.8556. Min Range: -3.8556

Max Act: 3.7305. Min Act: -0.1700

Data Index: 1332295 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 3.8556. Min Range: -3.8556

Max Act: 3.6992. Min Act: -0.1700

Data Index: 564284 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 3.8556. Min Range: -3.8556

Max Act: 3.6992. Min Act: -0.1700

Data Index: 592216 (C4 (Web Text))

Max Activating Token Index: 546

Text #7

Max Range: 3.8556. Min Range: -3.8556

Max Act: 3.6992. Min Act: -0.1700

Data Index: 770507 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 3.8556. Min Range: -3.8556

Max Act: 3.6679. Min Act: -0.1700

Data Index: 1128805 (C4 (Web Text))

Max Activating Token Index: 316

Text #9

Max Range: 3.8556. Min Range: -3.8556

Max Act: 3.6679. Min Act: -0.1700

Data Index: 1081714 (C4 (Web Text))

Max Activating Token Index: 435

Text #10

Max Range: 3.8556. Min Range: -3.8556

Max Act: 3.6679. Min Act: -0.1700

Data Index: 1310152 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 3.8556. Min Range: -3.8556

Max Act: 3.6366. Min Act: -0.1700

Data Index: 455917 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 3.8556. Min Range: -3.8556

Max Act: 3.6679. Min Act: -0.1700

Data Index: 1134701 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 3.8556. Min Range: -3.8556

Max Act: 3.6053. Min Act: -0.1700

Data Index: 1143769 (C4 (Web Text))

Max Activating Token Index: 854

Text #14

Max Range: 3.8556. Min Range: -3.8556

Max Act: 3.6366. Min Act: -0.1700

Data Index: 440160 (C4 (Web Text))

Max Activating Token Index: 695

Text #15

Max Range: 3.8556. Min Range: -3.8556

Max Act: 3.6053. Min Act: -0.1700

Data Index: 1289507 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 3.8556. Min Range: -3.8556

Max Act: 3.6053. Min Act: -0.1700

Data Index: 598962 (C4 (Web Text))

Max Activating Token Index: 557

Text #17

Max Range: 3.8556. Min Range: -3.8556

Max Act: 3.6053. Min Act: -0.1700

Data Index: 82703 (C4 (Web Text))

Max Activating Token Index: 153

Text #18

Max Range: 3.8556. Min Range: -3.8556

Max Act: 3.6366. Min Act: -0.1700

Data Index: 463499 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 3.8556. Min Range: -3.8556

Max Act: 3.6053. Min Act: -0.1700

Data Index: 638003 (C4 (Web Text))

Max Activating Token Index: 148