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

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

Neuron 1053 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0265. Min Range: -1.0265

Max Act: 1.0265. Min Act: -0.0000

Data Index: 703404 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.7342. Min Act: -0.0000

Data Index: 134859 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.4419. Min Act: -0.0000

Data Index: 752449 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.6312. Min Act: -0.0000

Data Index: 440485 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.6377. Min Act: -0.0000

Data Index: 889778 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.5663. Min Act: -0.0000

Data Index: 1033109 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.5236. Min Act: -0.0000

Data Index: 468505 (C4 (Web Text))

Max Activating Token Index: 298

Text #7

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.5014. Min Act: -0.0000

Data Index: 768308 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.4519. Min Act: -0.0000

Data Index: 958841 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.4783. Min Act: -0.0000

Data Index: 344122 (C4 (Web Text))

Max Activating Token Index: 986

Text #10

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.4568. Min Act: -0.0000

Data Index: 1198879 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.4307. Min Act: -0.0000

Data Index: 370353 (C4 (Web Text))

Max Activating Token Index: 719

Text #12

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.4868. Min Act: -0.0000

Data Index: 148434 (C4 (Web Text))

Max Activating Token Index: 423

Text #13

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.4002. Min Act: -0.0000

Data Index: 855050 (C4 (Web Text))

Max Activating Token Index: 110

Text #14

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.4225. Min Act: -0.0000

Data Index: 290436 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.4063. Min Act: -0.0000

Data Index: 1337486 (C4 (Web Text))

Max Activating Token Index: 838

Text #16

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.3996. Min Act: -0.0000

Data Index: 1529494 (Python Code)

Max Activating Token Index: 755

Text #17

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.3604. Min Act: -0.0000

Data Index: 882919 (C4 (Web Text))

Max Activating Token Index: 294

Text #18

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.2939. Min Act: -0.0000

Data Index: 74616 (C4 (Web Text))

Max Activating Token Index: 867

Text #19

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.3760. Min Act: -0.0000

Data Index: 1077726 (C4 (Web Text))

Max Activating Token Index: 1003