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

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

Neuron 4592 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: 5.3212. Min Range: -5.3212

Max Act: 5.3212. Min Act: -0.0001

Data Index: 1170364 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 5.3212. Min Range: -5.3212

Max Act: 5.2025. Min Act: -0.0001

Data Index: 801692 (C4 (Web Text))

Max Activating Token Index: 82

Text #2

Max Range: 5.3212. Min Range: -5.3212

Max Act: 4.7960. Min Act: -0.0001

Data Index: 1358513 (C4 (Web Text))

Max Activating Token Index: 761

Text #3

Max Range: 5.3212. Min Range: -5.3212

Max Act: 4.4331. Min Act: -0.0001

Data Index: 352776 (C4 (Web Text))

Max Activating Token Index: 236

Text #4

Max Range: 5.3212. Min Range: -5.3212

Max Act: 4.5853. Min Act: -0.0001

Data Index: 979607 (C4 (Web Text))

Max Activating Token Index: 373

Text #5

Max Range: 5.3212. Min Range: -5.3212

Max Act: 4.6845. Min Act: -0.0001

Data Index: 217718 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 5.3212. Min Range: -5.3212

Max Act: 4.1829. Min Act: -0.0001

Data Index: 1070174 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 5.3212. Min Range: -5.3212

Max Act: 4.1396. Min Act: -0.0001

Data Index: 626371 (C4 (Web Text))

Max Activating Token Index: 396

Text #8

Max Range: 5.3212. Min Range: -5.3212

Max Act: 4.4727. Min Act: -0.0001

Data Index: 1278820 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 5.3212. Min Range: -5.3212

Max Act: 4.2702. Min Act: -0.0001

Data Index: 492933 (C4 (Web Text))

Max Activating Token Index: 104

Text #10

Max Range: 5.3212. Min Range: -5.3212

Max Act: 4.1972. Min Act: -0.0001

Data Index: 348977 (C4 (Web Text))

Max Activating Token Index: 562

Text #11

Max Range: 5.3212. Min Range: -5.3212

Max Act: 3.6860. Min Act: -0.0001

Data Index: 763600 (C4 (Web Text))

Max Activating Token Index: 739

Text #12

Max Range: 5.3212. Min Range: -5.3212

Max Act: 3.8705. Min Act: -0.0001

Data Index: 926740 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 5.3212. Min Range: -5.3212

Max Act: 3.8338. Min Act: -0.0001

Data Index: 642369 (C4 (Web Text))

Max Activating Token Index: 59

Text #14

Max Range: 5.3212. Min Range: -5.3212

Max Act: 3.8226. Min Act: -0.0001

Data Index: 152077 (C4 (Web Text))

Max Activating Token Index: 535

Text #15

Max Range: 5.3212. Min Range: -5.3212

Max Act: 4.0054. Min Act: -0.0001

Data Index: 947227 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 5.3212. Min Range: -5.3212

Max Act: 4.0105. Min Act: -0.0001

Data Index: 181044 (C4 (Web Text))

Max Activating Token Index: 692

Text #17

Max Range: 5.3212. Min Range: -5.3212

Max Act: 3.5968. Min Act: -0.0001

Data Index: 1057918 (C4 (Web Text))

Max Activating Token Index: 954

Text #18

Max Range: 5.3212. Min Range: -5.3212

Max Act: 3.9061. Min Act: -0.0001

Data Index: 446494 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 5.3212. Min Range: -5.3212

Max Act: 3.5401. Min Act: -0.0001

Data Index: 843151 (C4 (Web Text))

Max Activating Token Index: 995