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

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

Neuron 513 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: 0.1029. Min Range: -0.1029

Max Act: 0.1029. Min Act: -0.0000

Data Index: 113417 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0371. Min Act: -0.0001

Data Index: 616512 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0836. Min Act: -0.0001

Data Index: 1352554 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0562. Min Act: -0.0000

Data Index: 1207517 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0696. Min Act: -0.0001

Data Index: 1076219 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0575. Min Act: -0.0000

Data Index: 330212 (C4 (Web Text))

Max Activating Token Index: 186

Text #6

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0420. Min Act: -0.0000

Data Index: 1111258 (C4 (Web Text))

Max Activating Token Index: 960

Text #7

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0536. Min Act: -0.0000

Data Index: 1192715 (C4 (Web Text))

Max Activating Token Index: 348

Text #8

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0494. Min Act: -0.0000

Data Index: 1238781 (C4 (Web Text))

Max Activating Token Index: 244

Text #9

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0530. Min Act: -0.0001

Data Index: 286335 (C4 (Web Text))

Max Activating Token Index: 958

Text #10

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0488. Min Act: -0.0001

Data Index: 1646772 (Python Code)

Max Activating Token Index: 68

Text #11

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0504. Min Act: -0.0000

Data Index: 634624 (C4 (Web Text))

Max Activating Token Index: 189

Text #12

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0501. Min Act: -0.0000

Data Index: 103884 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0488. Min Act: -0.0000

Data Index: 377412 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0489. Min Act: -0.0000

Data Index: 741217 (C4 (Web Text))

Max Activating Token Index: 858

Text #15

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0353. Min Act: -0.0000

Data Index: 222746 (C4 (Web Text))

Max Activating Token Index: 954

Text #16

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0423. Min Act: -0.0001

Data Index: 765932 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0469. Min Act: -0.0001

Data Index: 1603067 (Python Code)

Max Activating Token Index: 895

Text #18

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0561. Min Act: -0.0001

Data Index: 1211752 (C4 (Web Text))

Max Activating Token Index: 910

Text #19

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0458. Min Act: -0.0000

Data Index: 458244 (C4 (Web Text))

Max Activating Token Index: 10