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

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

Neuron 1234 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6470. Min Range: -2.6470

Max Act: 2.6470. Min Act: -0.0000

Data Index: 17920 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 2.6470. Min Range: -2.6470

Max Act: 2.4018. Min Act: -0.0000

Data Index: 1346513 (C4 (Web Text))

Max Activating Token Index: 818

Text #2

Max Range: 2.6470. Min Range: -2.6470

Max Act: 2.0934. Min Act: -0.0000

Data Index: 1238295 (C4 (Web Text))

Max Activating Token Index: 854

Text #3

Max Range: 2.6470. Min Range: -2.6470

Max Act: 2.3313. Min Act: -0.0000

Data Index: 701539 (C4 (Web Text))

Max Activating Token Index: 372

Text #4

Max Range: 2.6470. Min Range: -2.6470

Max Act: 1.9672. Min Act: -0.0000

Data Index: 744691 (C4 (Web Text))

Max Activating Token Index: 253

Text #5

Max Range: 2.6470. Min Range: -2.6470

Max Act: 1.9292. Min Act: -0.0000

Data Index: 988542 (C4 (Web Text))

Max Activating Token Index: 495

Text #6

Max Range: 2.6470. Min Range: -2.6470

Max Act: 1.9739. Min Act: -0.0000

Data Index: 1170190 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 2.6470. Min Range: -2.6470

Max Act: 1.9518. Min Act: -0.0000

Data Index: 171349 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 2.6470. Min Range: -2.6470

Max Act: 1.8746. Min Act: -0.0000

Data Index: 347992 (C4 (Web Text))

Max Activating Token Index: 195

Text #9

Max Range: 2.6470. Min Range: -2.6470

Max Act: 1.9004. Min Act: -0.0000

Data Index: 234850 (C4 (Web Text))

Max Activating Token Index: 791

Text #10

Max Range: 2.6470. Min Range: -2.6470

Max Act: 1.8754. Min Act: -0.0000

Data Index: 226880 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 2.6470. Min Range: -2.6470

Max Act: 1.7894. Min Act: -0.0000

Data Index: 98035 (C4 (Web Text))

Max Activating Token Index: 804

Text #12

Max Range: 2.6470. Min Range: -2.6470

Max Act: 1.7822. Min Act: -0.0000

Data Index: 587273 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 2.6470. Min Range: -2.6470

Max Act: 1.7842. Min Act: -0.0000

Data Index: 1251934 (C4 (Web Text))

Max Activating Token Index: 142

Text #14

Max Range: 2.6470. Min Range: -2.6470

Max Act: 1.6616. Min Act: -0.0000

Data Index: 1286915 (C4 (Web Text))

Max Activating Token Index: 992

Text #15

Max Range: 2.6470. Min Range: -2.6470

Max Act: 1.8697. Min Act: -0.0000

Data Index: 997095 (C4 (Web Text))

Max Activating Token Index: 665

Text #16

Max Range: 2.6470. Min Range: -2.6470

Max Act: 1.9344. Min Act: -0.0000

Data Index: 816382 (C4 (Web Text))

Max Activating Token Index: 227

Text #17

Max Range: 2.6470. Min Range: -2.6470

Max Act: 1.7985. Min Act: -0.0000

Data Index: 951466 (C4 (Web Text))

Max Activating Token Index: 502

Text #18

Max Range: 2.6470. Min Range: -2.6470

Max Act: 1.5895. Min Act: -0.0000

Data Index: 268449 (C4 (Web Text))

Max Activating Token Index: 149

Text #19

Max Range: 2.6470. Min Range: -2.6470

Max Act: 1.6817. Min Act: -0.0000

Data Index: 915392 (C4 (Web Text))

Max Activating Token Index: 707