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

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

Neuron 3676 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: 2.8404. Min Range: -2.8404

Max Act: 2.8404. Min Act: -0.0000

Data Index: 189311 (C4 (Web Text))

Max Activating Token Index: 641

Text #1

Max Range: 2.8404. Min Range: -2.8404

Max Act: 2.4671. Min Act: -0.0000

Data Index: 328943 (C4 (Web Text))

Max Activating Token Index: 338

Text #2

Max Range: 2.8404. Min Range: -2.8404

Max Act: 2.1936. Min Act: -0.0001

Data Index: 355108 (C4 (Web Text))

Max Activating Token Index: 486

Text #3

Max Range: 2.8404. Min Range: -2.8404

Max Act: 2.2349. Min Act: -0.0000

Data Index: 1139335 (C4 (Web Text))

Max Activating Token Index: 827

Text #4

Max Range: 2.8404. Min Range: -2.8404

Max Act: 2.1897. Min Act: -0.0000

Data Index: 103470 (C4 (Web Text))

Max Activating Token Index: 950

Text #5

Max Range: 2.8404. Min Range: -2.8404

Max Act: 2.0719. Min Act: -0.0000

Data Index: 949840 (C4 (Web Text))

Max Activating Token Index: 685

Text #6

Max Range: 2.8404. Min Range: -2.8404

Max Act: 2.1263. Min Act: -0.0000

Data Index: 72032 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 2.8404. Min Range: -2.8404

Max Act: 2.1231. Min Act: -0.0000

Data Index: 361293 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 2.8404. Min Range: -2.8404

Max Act: 1.9848. Min Act: -0.0000

Data Index: 363154 (C4 (Web Text))

Max Activating Token Index: 869

Text #9

Max Range: 2.8404. Min Range: -2.8404

Max Act: 2.0052. Min Act: -0.0000

Data Index: 993106 (C4 (Web Text))

Max Activating Token Index: 341

Text #10

Max Range: 2.8404. Min Range: -2.8404

Max Act: 2.1730. Min Act: -0.0000

Data Index: 1021339 (C4 (Web Text))

Max Activating Token Index: 1018

Text #11

Max Range: 2.8404. Min Range: -2.8404

Max Act: 1.9526. Min Act: -0.0000

Data Index: 645516 (C4 (Web Text))

Max Activating Token Index: 986

Text #12

Max Range: 2.8404. Min Range: -2.8404

Max Act: 2.0460. Min Act: -0.0000

Data Index: 388602 (C4 (Web Text))

Max Activating Token Index: 352

Text #13

Max Range: 2.8404. Min Range: -2.8404

Max Act: 2.0250. Min Act: -0.0000

Data Index: 124012 (C4 (Web Text))

Max Activating Token Index: 804

Text #14

Max Range: 2.8404. Min Range: -2.8404

Max Act: 2.1087. Min Act: -0.0000

Data Index: 198155 (C4 (Web Text))

Max Activating Token Index: 149

Text #15

Max Range: 2.8404. Min Range: -2.8404

Max Act: 2.0000. Min Act: -0.0000

Data Index: 1323497 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 2.8404. Min Range: -2.8404

Max Act: 1.9848. Min Act: -0.0000

Data Index: 918626 (C4 (Web Text))

Max Activating Token Index: 947

Text #17

Max Range: 2.8404. Min Range: -2.8404

Max Act: 1.7672. Min Act: -0.0000

Data Index: 1054656 (C4 (Web Text))

Max Activating Token Index: 1021

Text #18

Max Range: 2.8404. Min Range: -2.8404

Max Act: 1.7661. Min Act: -0.0000

Data Index: 60370 (C4 (Web Text))

Max Activating Token Index: 823

Text #19

Max Range: 2.8404. Min Range: -2.8404

Max Act: 2.0727. Min Act: -0.0000

Data Index: 1358849 (C4 (Web Text))

Max Activating Token Index: 952