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

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

Neuron 5100 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.7746. Min Act: -0.0001

Data Index: 211574 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.7433. Min Act: -0.0001

Data Index: 659234 (C4 (Web Text))

Max Activating Token Index: 735

Text #2

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.7450. Min Act: -0.0001

Data Index: 413508 (C4 (Web Text))

Max Activating Token Index: 467

Text #3

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.6438. Min Act: -0.0001

Data Index: 1188088 (C4 (Web Text))

Max Activating Token Index: 811

Text #4

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.6866. Min Act: -0.0001

Data Index: 1138342 (C4 (Web Text))

Max Activating Token Index: 6

Text #5

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.6775. Min Act: -0.0001

Data Index: 1044377 (C4 (Web Text))

Max Activating Token Index: 444

Text #6

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.6732. Min Act: -0.0001

Data Index: 896094 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.6569. Min Act: -0.0001

Data Index: 1257448 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.6711. Min Act: -0.0001

Data Index: 176470 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.6926. Min Act: -0.0001

Data Index: 79468 (C4 (Web Text))

Max Activating Token Index: 157

Text #10

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.6657. Min Act: -0.0001

Data Index: 1017475 (C4 (Web Text))

Max Activating Token Index: 647

Text #11

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.6629. Min Act: -0.0001

Data Index: 719277 (C4 (Web Text))

Max Activating Token Index: 514

Text #12

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.6582. Min Act: -0.0001

Data Index: 84751 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.6376. Min Act: -0.0001

Data Index: 360533 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.7101. Min Act: -0.0001

Data Index: 363752 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.6423. Min Act: -0.0001

Data Index: 844872 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.6405. Min Act: -0.0001

Data Index: 1224231 (C4 (Web Text))

Max Activating Token Index: 991

Text #17

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.6113. Min Act: -0.0001

Data Index: 259916 (C4 (Web Text))

Max Activating Token Index: 106

Text #18

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.6231. Min Act: -0.0001

Data Index: 1254873 (C4 (Web Text))

Max Activating Token Index: 316

Text #19

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.6040. Min Act: -0.0001

Data Index: 1353029 (C4 (Web Text))

Max Activating Token Index: 376