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

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

Neuron 1476 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: 3.2631. Min Range: -3.2631

Max Act: 3.2631. Min Act: -0.1700

Data Index: 33493 (C4 (Web Text))

Max Activating Token Index: 324

Text #1

Max Range: 3.2631. Min Range: -3.2631

Max Act: 3.2160. Min Act: -0.1700

Data Index: 119929 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 3.2631. Min Range: -3.2631

Max Act: 3.2160. Min Act: -0.1700

Data Index: 735489 (C4 (Web Text))

Max Activating Token Index: 676

Text #3

Max Range: 3.2631. Min Range: -3.2631

Max Act: 3.2003. Min Act: -0.1700

Data Index: 339182 (C4 (Web Text))

Max Activating Token Index: 364

Text #4

Max Range: 3.2631. Min Range: -3.2631

Max Act: 3.2003. Min Act: -0.1700

Data Index: 101500 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 3.2631. Min Range: -3.2631

Max Act: 3.1530. Min Act: -0.1700

Data Index: 130691 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 3.2631. Min Range: -3.2631

Max Act: 3.1373. Min Act: -0.1700

Data Index: 756849 (C4 (Web Text))

Max Activating Token Index: 892

Text #7

Max Range: 3.2631. Min Range: -3.2631

Max Act: 3.1530. Min Act: -0.1700

Data Index: 243336 (C4 (Web Text))

Max Activating Token Index: 520

Text #8

Max Range: 3.2631. Min Range: -3.2631

Max Act: 3.1530. Min Act: -0.1700

Data Index: 207524 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 3.2631. Min Range: -3.2631

Max Act: 3.1688. Min Act: -0.1700

Data Index: 144394 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 3.2631. Min Range: -3.2631

Max Act: 3.1058. Min Act: -0.1700

Data Index: 388973 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 3.2631. Min Range: -3.2631

Max Act: 3.0742. Min Act: -0.1700

Data Index: 57893 (C4 (Web Text))

Max Activating Token Index: 906

Text #12

Max Range: 3.2631. Min Range: -3.2631

Max Act: 3.0742. Min Act: -0.1700

Data Index: 548369 (C4 (Web Text))

Max Activating Token Index: 520

Text #13

Max Range: 3.2631. Min Range: -3.2631

Max Act: 3.0742. Min Act: -0.1700

Data Index: 391451 (C4 (Web Text))

Max Activating Token Index: 873

Text #14

Max Range: 3.2631. Min Range: -3.2631

Max Act: 3.0584. Min Act: -0.1700

Data Index: 243436 (C4 (Web Text))

Max Activating Token Index: 304

Text #15

Max Range: 3.2631. Min Range: -3.2631

Max Act: 3.0900. Min Act: -0.1700

Data Index: 964894 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 3.2631. Min Range: -3.2631

Max Act: 3.0269. Min Act: -0.1700

Data Index: 44146 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 3.2631. Min Range: -3.2631

Max Act: 3.0111. Min Act: -0.1700

Data Index: 614561 (C4 (Web Text))

Max Activating Token Index: 941

Text #18

Max Range: 3.2631. Min Range: -3.2631

Max Act: 3.0269. Min Act: -0.1700

Data Index: 54529 (C4 (Web Text))

Max Activating Token Index: 615

Text #19

Max Range: 3.2631. Min Range: -3.2631

Max Act: 3.0269. Min Act: -0.1700

Data Index: 421243 (C4 (Web Text))

Max Activating Token Index: 679