Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1773 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.9329. Min Range: -3.9329

Max Act: 3.8703. Min Act: -0.1700

Data Index: 47890 (C4 (Web Text))

Max Activating Token Index: 803

Text #1

Max Range: 3.9329. Min Range: -3.9329

Max Act: 3.9329. Min Act: -0.1700

Data Index: 622616 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 3.9329. Min Range: -3.9329

Max Act: 3.8703. Min Act: -0.1700

Data Index: 674392 (C4 (Web Text))

Max Activating Token Index: 254

Text #3

Max Range: 3.9329. Min Range: -3.9329

Max Act: 3.8078. Min Act: -0.1700

Data Index: 369911 (C4 (Web Text))

Max Activating Token Index: 763

Text #4

Max Range: 3.9329. Min Range: -3.9329

Max Act: 3.8078. Min Act: -0.1700

Data Index: 911695 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 3.9329. Min Range: -3.9329

Max Act: 3.8078. Min Act: -0.1700

Data Index: 1270735 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 3.9329. Min Range: -3.9329

Max Act: 3.7139. Min Act: -0.1700

Data Index: 1242126 (C4 (Web Text))

Max Activating Token Index: 849

Text #7

Max Range: 3.9329. Min Range: -3.9329

Max Act: 3.7139. Min Act: -0.1700

Data Index: 1265769 (C4 (Web Text))

Max Activating Token Index: 593

Text #8

Max Range: 3.9329. Min Range: -3.9329

Max Act: 3.7452. Min Act: -0.1700

Data Index: 829993 (C4 (Web Text))

Max Activating Token Index: 926

Text #9

Max Range: 3.9329. Min Range: -3.9329

Max Act: 3.6826. Min Act: -0.1700

Data Index: 1294979 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 3.9329. Min Range: -3.9329

Max Act: 3.7139. Min Act: -0.1700

Data Index: 28521 (C4 (Web Text))

Max Activating Token Index: 546

Text #11

Max Range: 3.9329. Min Range: -3.9329

Max Act: 3.6826. Min Act: -0.1700

Data Index: 601188 (C4 (Web Text))

Max Activating Token Index: 323

Text #12

Max Range: 3.9329. Min Range: -3.9329

Max Act: 3.6513. Min Act: -0.1700

Data Index: 360394 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 3.9329. Min Range: -3.9329

Max Act: 3.7139. Min Act: -0.1700

Data Index: 754053 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 3.9329. Min Range: -3.9329

Max Act: 3.6826. Min Act: -0.1700

Data Index: 792087 (C4 (Web Text))

Max Activating Token Index: 488

Text #15

Max Range: 3.9329. Min Range: -3.9329

Max Act: 3.6826. Min Act: -0.1700

Data Index: 477626 (C4 (Web Text))

Max Activating Token Index: 553

Text #16

Max Range: 3.9329. Min Range: -3.9329

Max Act: 3.6826. Min Act: -0.1700

Data Index: 499305 (C4 (Web Text))

Max Activating Token Index: 802

Text #17

Max Range: 3.9329. Min Range: -3.9329

Max Act: 3.6513. Min Act: -0.1700

Data Index: 477706 (C4 (Web Text))

Max Activating Token Index: 574

Text #18

Max Range: 3.9329. Min Range: -3.9329

Max Act: 3.6200. Min Act: -0.1700

Data Index: 204331 (C4 (Web Text))

Max Activating Token Index: 914

Text #19

Max Range: 3.9329. Min Range: -3.9329

Max Act: 3.5574. Min Act: -0.1700

Data Index: 930289 (C4 (Web Text))

Max Activating Token Index: 421