Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1904 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1433. Min Range: -1.1433

Max Act: 1.1433. Min Act: -0.0000

Data Index: 251501 (C4 (Web Text))

Max Activating Token Index: 881

Text #1

Max Range: 1.1433. Min Range: -1.1433

Max Act: 1.0197. Min Act: -0.0000

Data Index: 640963 (C4 (Web Text))

Max Activating Token Index: 553

Text #2

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.8822. Min Act: -0.0000

Data Index: 1062411 (C4 (Web Text))

Max Activating Token Index: 858

Text #3

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.8595. Min Act: -0.0000

Data Index: 1294309 (C4 (Web Text))

Max Activating Token Index: 680

Text #4

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.8549. Min Act: -0.0000

Data Index: 861825 (C4 (Web Text))

Max Activating Token Index: 550

Text #5

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.8157. Min Act: -0.0000

Data Index: 532405 (C4 (Web Text))

Max Activating Token Index: 960

Text #6

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.7979. Min Act: -0.0000

Data Index: 1236169 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.7911. Min Act: -0.0000

Data Index: 635436 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.7933. Min Act: -0.0000

Data Index: 114552 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.7544. Min Act: -0.0000

Data Index: 278651 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.7404. Min Act: -0.0000

Data Index: 75502 (C4 (Web Text))

Max Activating Token Index: 333

Text #11

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.6876. Min Act: -0.0000

Data Index: 326909 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.7360. Min Act: -0.0000

Data Index: 324281 (C4 (Web Text))

Max Activating Token Index: 986

Text #13

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.6812. Min Act: -0.0000

Data Index: 225726 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.6866. Min Act: -0.0000

Data Index: 193704 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.7044. Min Act: -0.0000

Data Index: 177877 (C4 (Web Text))

Max Activating Token Index: 524

Text #16

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.7282. Min Act: -0.0000

Data Index: 1066071 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.6796. Min Act: -0.0000

Data Index: 1056296 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.6834. Min Act: -0.0000

Data Index: 282607 (C4 (Web Text))

Max Activating Token Index: 186

Text #19

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.6611. Min Act: -0.0000

Data Index: 545709 (C4 (Web Text))

Max Activating Token Index: 15