Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 873 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 2.8563. Min Range: -2.8563

Max Act: 2.8563. Min Act: -0.1700

Data Index: 894216 (C4 (Web Text))

Max Activating Token Index: 419

Text #1

Max Range: 2.8563. Min Range: -2.8563

Max Act: 2.8250. Min Act: -0.1620

Data Index: 340022 (C4 (Web Text))

Max Activating Token Index: 769

Text #2

Max Range: 2.8563. Min Range: -2.8563

Max Act: 2.7699. Min Act: -0.1700

Data Index: 1303234 (C4 (Web Text))

Max Activating Token Index: 417

Text #3

Max Range: 2.8563. Min Range: -2.8563

Max Act: 2.7348. Min Act: -0.1700

Data Index: 970202 (C4 (Web Text))

Max Activating Token Index: 559

Text #4

Max Range: 2.8563. Min Range: -2.8563

Max Act: 2.7266. Min Act: -0.1700

Data Index: 348622 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 2.8563. Min Range: -2.8563

Max Act: 2.7195. Min Act: -0.1699

Data Index: 1299883 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 2.8563. Min Range: -2.8563

Max Act: 2.7068. Min Act: -0.1700

Data Index: 1368450 (Python Code)

Max Activating Token Index: 730

Text #7

Max Range: 2.8563. Min Range: -2.8563

Max Act: 2.7074. Min Act: -0.1666

Data Index: 468506 (C4 (Web Text))

Max Activating Token Index: 801

Text #8

Max Range: 2.8563. Min Range: -2.8563

Max Act: 2.7032. Min Act: -0.1700

Data Index: 790616 (C4 (Web Text))

Max Activating Token Index: 754

Text #9

Max Range: 2.8563. Min Range: -2.8563

Max Act: 2.7074. Min Act: -0.1700

Data Index: 1089074 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 2.8563. Min Range: -2.8563

Max Act: 2.7108. Min Act: -0.1700

Data Index: 767402 (C4 (Web Text))

Max Activating Token Index: 487

Text #11

Max Range: 2.8563. Min Range: -2.8563

Max Act: 2.7011. Min Act: -0.1649

Data Index: 28988 (C4 (Web Text))

Max Activating Token Index: 785

Text #12

Max Range: 2.8563. Min Range: -2.8563

Max Act: 2.6990. Min Act: -0.1700

Data Index: 16566 (C4 (Web Text))

Max Activating Token Index: 929

Text #13

Max Range: 2.8563. Min Range: -2.8563

Max Act: 2.7011. Min Act: -0.1700

Data Index: 426026 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 2.8563. Min Range: -2.8563

Max Act: 2.6870. Min Act: -0.1700

Data Index: 50840 (C4 (Web Text))

Max Activating Token Index: 378

Text #15

Max Range: 2.8563. Min Range: -2.8563

Max Act: 2.7029. Min Act: -0.1700

Data Index: 252932 (C4 (Web Text))

Max Activating Token Index: 762

Text #16

Max Range: 2.8563. Min Range: -2.8563

Max Act: 2.6881. Min Act: -0.1699

Data Index: 1378686 (Python Code)

Max Activating Token Index: 715

Text #17

Max Range: 2.8563. Min Range: -2.8563

Max Act: 2.6716. Min Act: -0.1700

Data Index: 834594 (C4 (Web Text))

Max Activating Token Index: 763

Text #18

Max Range: 2.8563. Min Range: -2.8563

Max Act: 2.6726. Min Act: -0.1696

Data Index: 1614929 (Python Code)

Max Activating Token Index: 704

Text #19

Max Range: 2.8563. Min Range: -2.8563

Max Act: 2.6655. Min Act: -0.1700

Data Index: 1610600 (Python Code)

Max Activating Token Index: 876