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

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

Neuron 3919 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.4904. Min Act: -0.0000

Data Index: 688934 (C4 (Web Text))

Max Activating Token Index: 322

Text #1

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.5164. Min Act: -0.0000

Data Index: 91003 (C4 (Web Text))

Max Activating Token Index: 420

Text #2

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.4979. Min Act: -0.0000

Data Index: 738083 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.4901. Min Act: 0.0000

Data Index: 1341096 (C4 (Web Text))

Max Activating Token Index: 1010

Text #4

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.4598. Min Act: -0.0000

Data Index: 889045 (C4 (Web Text))

Max Activating Token Index: 226

Text #5

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.4699. Min Act: -0.0000

Data Index: 1304368 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.4516. Min Act: -0.0000

Data Index: 302882 (C4 (Web Text))

Max Activating Token Index: 65

Text #7

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.4581. Min Act: -0.0000

Data Index: 47330 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.4344. Min Act: -0.0000

Data Index: 263709 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.4036. Min Act: -0.0000

Data Index: 250270 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.4195. Min Act: -0.0000

Data Index: 357677 (C4 (Web Text))

Max Activating Token Index: 62

Text #11

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.4098. Min Act: 0.0000

Data Index: 849058 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.4065. Min Act: -0.0000

Data Index: 91909 (C4 (Web Text))

Max Activating Token Index: 420

Text #13

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.3957. Min Act: -0.0000

Data Index: 893458 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.4121. Min Act: -0.0000

Data Index: 285222 (C4 (Web Text))

Max Activating Token Index: 588

Text #15

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.3905. Min Act: -0.0000

Data Index: 380335 (C4 (Web Text))

Max Activating Token Index: 86

Text #16

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.3757. Min Act: 0.0000

Data Index: 394048 (C4 (Web Text))

Max Activating Token Index: 757

Text #17

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.3863. Min Act: -0.0000

Data Index: 508978 (C4 (Web Text))

Max Activating Token Index: 669

Text #18

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.3962. Min Act: 0.0000

Data Index: 21128 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.3973. Min Act: -0.0000

Data Index: 979722 (C4 (Web Text))

Max Activating Token Index: 273