Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1170 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3721. Min Act: -0.0001

Data Index: 1186013 (C4 (Web Text))

Max Activating Token Index: 238

Text #1

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3551. Min Act: -0.0000

Data Index: 83486 (C4 (Web Text))

Max Activating Token Index: 91

Text #2

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3499. Min Act: -0.0000

Data Index: 722081 (C4 (Web Text))

Max Activating Token Index: 549

Text #3

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3357. Min Act: -0.0001

Data Index: 1342550 (C4 (Web Text))

Max Activating Token Index: 904

Text #4

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3296. Min Act: -0.0000

Data Index: 927253 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3132. Min Act: -0.0000

Data Index: 1020619 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3115. Min Act: -0.0000

Data Index: 335536 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2903. Min Act: -0.0000

Data Index: 1233047 (C4 (Web Text))

Max Activating Token Index: 877

Text #8

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3067. Min Act: -0.0001

Data Index: 1356681 (C4 (Web Text))

Max Activating Token Index: 120

Text #9

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2892. Min Act: -0.0001

Data Index: 353099 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2891. Min Act: -0.0000

Data Index: 1260722 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2901. Min Act: -0.0001

Data Index: 1117956 (C4 (Web Text))

Max Activating Token Index: 838

Text #12

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2993. Min Act: -0.0000

Data Index: 267358 (C4 (Web Text))

Max Activating Token Index: 510

Text #13

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2785. Min Act: -0.0000

Data Index: 852760 (C4 (Web Text))

Max Activating Token Index: 70

Text #14

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2593. Min Act: -0.0001

Data Index: 495078 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2728. Min Act: -0.0000

Data Index: 840536 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2732. Min Act: -0.0000

Data Index: 1088471 (C4 (Web Text))

Max Activating Token Index: 698

Text #17

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2562. Min Act: -0.0001

Data Index: 599279 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2554. Min Act: -0.0000

Data Index: 659522 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2560. Min Act: -0.0000

Data Index: 786060 (C4 (Web Text))

Max Activating Token Index: 897