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

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

Neuron 2505 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5812. Min Range: -0.5812

Max Act: 0.5812. Min Act: -0.0000

Data Index: 744339 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 0.5812. Min Range: -0.5812

Max Act: 0.5189. Min Act: -0.0000

Data Index: 1330663 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 0.5812. Min Range: -0.5812

Max Act: 0.4938. Min Act: -0.0000

Data Index: 560027 (C4 (Web Text))

Max Activating Token Index: 935

Text #3

Max Range: 0.5812. Min Range: -0.5812

Max Act: 0.4550. Min Act: -0.0000

Data Index: 551703 (C4 (Web Text))

Max Activating Token Index: 972

Text #4

Max Range: 0.5812. Min Range: -0.5812

Max Act: 0.4667. Min Act: -0.0000

Data Index: 759307 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 0.5812. Min Range: -0.5812

Max Act: 0.3959. Min Act: -0.0000

Data Index: 308159 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 0.5812. Min Range: -0.5812

Max Act: 0.4358. Min Act: -0.0000

Data Index: 900162 (C4 (Web Text))

Max Activating Token Index: 447

Text #7

Max Range: 0.5812. Min Range: -0.5812

Max Act: 0.3946. Min Act: -0.0000

Data Index: 54982 (C4 (Web Text))

Max Activating Token Index: 130

Text #8

Max Range: 0.5812. Min Range: -0.5812

Max Act: 0.3989. Min Act: -0.0000

Data Index: 271502 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 0.5812. Min Range: -0.5812

Max Act: 0.3870. Min Act: -0.0000

Data Index: 869724 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 0.5812. Min Range: -0.5812

Max Act: 0.4012. Min Act: -0.0000

Data Index: 269781 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 0.5812. Min Range: -0.5812

Max Act: 0.3928. Min Act: -0.0000

Data Index: 1001698 (C4 (Web Text))

Max Activating Token Index: 894

Text #12

Max Range: 0.5812. Min Range: -0.5812

Max Act: 0.3827. Min Act: -0.0000

Data Index: 1064110 (C4 (Web Text))

Max Activating Token Index: 736

Text #13

Max Range: 0.5812. Min Range: -0.5812

Max Act: 0.4063. Min Act: -0.0000

Data Index: 16192 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 0.5812. Min Range: -0.5812

Max Act: 0.3786. Min Act: -0.0000

Data Index: 570166 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 0.5812. Min Range: -0.5812

Max Act: 0.3640. Min Act: -0.0000

Data Index: 282499 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 0.5812. Min Range: -0.5812

Max Act: 0.3699. Min Act: -0.0000

Data Index: 1265833 (C4 (Web Text))

Max Activating Token Index: 191

Text #17

Max Range: 0.5812. Min Range: -0.5812

Max Act: 0.3545. Min Act: -0.0000

Data Index: 692706 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 0.5812. Min Range: -0.5812

Max Act: 0.3539. Min Act: -0.0000

Data Index: 1262127 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 0.5812. Min Range: -0.5812

Max Act: 0.3588. Min Act: -0.0000

Data Index: 821727 (C4 (Web Text))

Max Activating Token Index: 114