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

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

Neuron 5832 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0389. Min Act: -0.0002

Data Index: 794530 (C4 (Web Text))

Max Activating Token Index: 602

Text #1

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0344. Min Act: -0.0002

Data Index: 98702 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0317. Min Act: -0.0002

Data Index: 312502 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0294. Min Act: -0.0002

Data Index: 1041424 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0297. Min Act: -0.0002

Data Index: 340494 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0285. Min Act: -0.0002

Data Index: 867654 (C4 (Web Text))

Max Activating Token Index: 851

Text #6

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0269. Min Act: -0.0002

Data Index: 79031 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0254. Min Act: -0.0002

Data Index: 317021 (C4 (Web Text))

Max Activating Token Index: 764

Text #8

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0275. Min Act: -0.0002

Data Index: 50955 (C4 (Web Text))

Max Activating Token Index: 611

Text #9

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0260. Min Act: -0.0002

Data Index: 793424 (C4 (Web Text))

Max Activating Token Index: 690

Text #10

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0290. Min Act: -0.0002

Data Index: 291351 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0261. Min Act: -0.0002

Data Index: 16750 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0253. Min Act: -0.0002

Data Index: 136246 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0258. Min Act: -0.0002

Data Index: 145860 (C4 (Web Text))

Max Activating Token Index: 769

Text #14

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0253. Min Act: -0.0002

Data Index: 1305921 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0267. Min Act: -0.0002

Data Index: 1093360 (C4 (Web Text))

Max Activating Token Index: 992

Text #16

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0235. Min Act: -0.0002

Data Index: 296817 (C4 (Web Text))

Max Activating Token Index: 842

Text #17

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0220. Min Act: -0.0002

Data Index: 129776 (C4 (Web Text))

Max Activating Token Index: 324

Text #18

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0242. Min Act: -0.0002

Data Index: 67488 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0214. Min Act: -0.0002

Data Index: 1014849 (C4 (Web Text))

Max Activating Token Index: 818