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

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

Neuron 4692 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9118. Min Range: -1.9118

Max Act: 1.9118. Min Act: -0.0001

Data Index: 1594319 (Python Code)

Max Activating Token Index: 57

Text #1

Max Range: 1.9118. Min Range: -1.9118

Max Act: 1.7285. Min Act: -0.0000

Data Index: 1397442 (Python Code)

Max Activating Token Index: 698

Text #2

Max Range: 1.9118. Min Range: -1.9118

Max Act: 1.6471. Min Act: -0.0000

Data Index: 1620665 (Python Code)

Max Activating Token Index: 616

Text #3

Max Range: 1.9118. Min Range: -1.9118

Max Act: 1.5997. Min Act: -0.0000

Data Index: 1472619 (Python Code)

Max Activating Token Index: 33

Text #4

Max Range: 1.9118. Min Range: -1.9118

Max Act: 1.5081. Min Act: -0.0000

Data Index: 1382555 (Python Code)

Max Activating Token Index: 42

Text #5

Max Range: 1.9118. Min Range: -1.9118

Max Act: 1.4039. Min Act: -0.0000

Data Index: 1403401 (Python Code)

Max Activating Token Index: 295

Text #6

Max Range: 1.9118. Min Range: -1.9118

Max Act: 1.3314. Min Act: -0.0000

Data Index: 1064200 (C4 (Web Text))

Max Activating Token Index: 147

Text #7

Max Range: 1.9118. Min Range: -1.9118

Max Act: 1.3262. Min Act: -0.0000

Data Index: 391828 (C4 (Web Text))

Max Activating Token Index: 578

Text #8

Max Range: 1.9118. Min Range: -1.9118

Max Act: 1.3357. Min Act: -0.0000

Data Index: 1313139 (C4 (Web Text))

Max Activating Token Index: 747

Text #9

Max Range: 1.9118. Min Range: -1.9118

Max Act: 1.3173. Min Act: -0.0001

Data Index: 1648224 (Python Code)

Max Activating Token Index: 254

Text #10

Max Range: 1.9118. Min Range: -1.9118

Max Act: 1.2852. Min Act: -0.0000

Data Index: 717322 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 1.9118. Min Range: -1.9118

Max Act: 1.2787. Min Act: -0.0000

Data Index: 1158096 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 1.9118. Min Range: -1.9118

Max Act: 1.1877. Min Act: -0.0000

Data Index: 24171 (C4 (Web Text))

Max Activating Token Index: 633

Text #13

Max Range: 1.9118. Min Range: -1.9118

Max Act: 1.2505. Min Act: -0.0000

Data Index: 753737 (C4 (Web Text))

Max Activating Token Index: 689

Text #14

Max Range: 1.9118. Min Range: -1.9118

Max Act: 1.1516. Min Act: -0.0000

Data Index: 794160 (C4 (Web Text))

Max Activating Token Index: 893

Text #15

Max Range: 1.9118. Min Range: -1.9118

Max Act: 1.0885. Min Act: -0.0000

Data Index: 380629 (C4 (Web Text))

Max Activating Token Index: 701

Text #16

Max Range: 1.9118. Min Range: -1.9118

Max Act: 1.2195. Min Act: -0.0000

Data Index: 111828 (C4 (Web Text))

Max Activating Token Index: 210

Text #17

Max Range: 1.9118. Min Range: -1.9118

Max Act: 1.2186. Min Act: -0.0000

Data Index: 520255 (C4 (Web Text))

Max Activating Token Index: 498

Text #18

Max Range: 1.9118. Min Range: -1.9118

Max Act: 1.2912. Min Act: -0.0000

Data Index: 795963 (C4 (Web Text))

Max Activating Token Index: 790

Text #19

Max Range: 1.9118. Min Range: -1.9118

Max Act: 1.1307. Min Act: -0.0000

Data Index: 389356 (C4 (Web Text))

Max Activating Token Index: 220