Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3697 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.2863. Min Range: -2.2863

Max Act: 2.2593. Min Act: -0.0000

Data Index: 1241369 (C4 (Web Text))

Max Activating Token Index: 212

Text #1

Max Range: 2.2863. Min Range: -2.2863

Max Act: 2.2557. Min Act: -0.0000

Data Index: 286358 (C4 (Web Text))

Max Activating Token Index: 604

Text #2

Max Range: 2.2863. Min Range: -2.2863

Max Act: 2.0735. Min Act: -0.0000

Data Index: 999549 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 2.2863. Min Range: -2.2863

Max Act: 1.9344. Min Act: -0.0000

Data Index: 652069 (C4 (Web Text))

Max Activating Token Index: 631

Text #4

Max Range: 2.2863. Min Range: -2.2863

Max Act: 2.2863. Min Act: -0.0000

Data Index: 622114 (C4 (Web Text))

Max Activating Token Index: 114

Text #5

Max Range: 2.2863. Min Range: -2.2863

Max Act: 2.0331. Min Act: -0.0000

Data Index: 375267 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 2.2863. Min Range: -2.2863

Max Act: 2.0117. Min Act: -0.0000

Data Index: 1064656 (C4 (Web Text))

Max Activating Token Index: 445

Text #7

Max Range: 2.2863. Min Range: -2.2863

Max Act: 1.9825. Min Act: -0.0000

Data Index: 598246 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 2.2863. Min Range: -2.2863

Max Act: 1.8600. Min Act: -0.0000

Data Index: 933236 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 2.2863. Min Range: -2.2863

Max Act: 1.9084. Min Act: -0.0000

Data Index: 1243066 (C4 (Web Text))

Max Activating Token Index: 128

Text #10

Max Range: 2.2863. Min Range: -2.2863

Max Act: 1.7677. Min Act: -0.0000

Data Index: 685756 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 2.2863. Min Range: -2.2863

Max Act: 1.8759. Min Act: -0.0000

Data Index: 619712 (C4 (Web Text))

Max Activating Token Index: 460

Text #12

Max Range: 2.2863. Min Range: -2.2863

Max Act: 1.8569. Min Act: -0.0000

Data Index: 73004 (C4 (Web Text))

Max Activating Token Index: 639

Text #13

Max Range: 2.2863. Min Range: -2.2863

Max Act: 1.7446. Min Act: -0.0000

Data Index: 766099 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 2.2863. Min Range: -2.2863

Max Act: 1.7488. Min Act: -0.0000

Data Index: 707608 (C4 (Web Text))

Max Activating Token Index: 602

Text #15

Max Range: 2.2863. Min Range: -2.2863

Max Act: 1.6330. Min Act: -0.0000

Data Index: 718109 (C4 (Web Text))

Max Activating Token Index: 156

Text #16

Max Range: 2.2863. Min Range: -2.2863

Max Act: 1.6096. Min Act: -0.0000

Data Index: 526025 (C4 (Web Text))

Max Activating Token Index: 918

Text #17

Max Range: 2.2863. Min Range: -2.2863

Max Act: 1.7200. Min Act: -0.0000

Data Index: 557081 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 2.2863. Min Range: -2.2863

Max Act: 1.7089. Min Act: -0.0000

Data Index: 878682 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 2.2863. Min Range: -2.2863

Max Act: 1.7023. Min Act: -0.0000

Data Index: 658220 (C4 (Web Text))

Max Activating Token Index: 334