Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4454 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6641. Min Range: -1.6641

Max Act: 1.6641. Min Act: -0.0000

Data Index: 139516 (C4 (Web Text))

Max Activating Token Index: 858

Text #1

Max Range: 1.6641. Min Range: -1.6641

Max Act: 1.5576. Min Act: -0.0000

Data Index: 1103139 (C4 (Web Text))

Max Activating Token Index: 376

Text #2

Max Range: 1.6641. Min Range: -1.6641

Max Act: 1.6491. Min Act: -0.0000

Data Index: 776747 (C4 (Web Text))

Max Activating Token Index: 865

Text #3

Max Range: 1.6641. Min Range: -1.6641

Max Act: 1.6222. Min Act: -0.0000

Data Index: 517224 (C4 (Web Text))

Max Activating Token Index: 488

Text #4

Max Range: 1.6641. Min Range: -1.6641

Max Act: 1.5999. Min Act: -0.0000

Data Index: 1052195 (C4 (Web Text))

Max Activating Token Index: 403

Text #5

Max Range: 1.6641. Min Range: -1.6641

Max Act: 1.5601. Min Act: -0.0000

Data Index: 1109496 (C4 (Web Text))

Max Activating Token Index: 670

Text #6

Max Range: 1.6641. Min Range: -1.6641

Max Act: 1.6424. Min Act: -0.0000

Data Index: 1610189 (Python Code)

Max Activating Token Index: 234

Text #7

Max Range: 1.6641. Min Range: -1.6641

Max Act: 1.4500. Min Act: -0.0000

Data Index: 866565 (C4 (Web Text))

Max Activating Token Index: 68

Text #8

Max Range: 1.6641. Min Range: -1.6641

Max Act: 1.5300. Min Act: -0.0000

Data Index: 1340658 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 1.6641. Min Range: -1.6641

Max Act: 1.5109. Min Act: -0.0000

Data Index: 1218813 (C4 (Web Text))

Max Activating Token Index: 948

Text #10

Max Range: 1.6641. Min Range: -1.6641

Max Act: 1.3363. Min Act: -0.0000

Data Index: 862800 (C4 (Web Text))

Max Activating Token Index: 959

Text #11

Max Range: 1.6641. Min Range: -1.6641

Max Act: 1.4797. Min Act: -0.0000

Data Index: 920624 (C4 (Web Text))

Max Activating Token Index: 158

Text #12

Max Range: 1.6641. Min Range: -1.6641

Max Act: 1.4634. Min Act: -0.0000

Data Index: 181541 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 1.6641. Min Range: -1.6641

Max Act: 1.3650. Min Act: -0.0000

Data Index: 271853 (C4 (Web Text))

Max Activating Token Index: 67

Text #14

Max Range: 1.6641. Min Range: -1.6641

Max Act: 1.5187. Min Act: -0.0000

Data Index: 214517 (C4 (Web Text))

Max Activating Token Index: 419

Text #15

Max Range: 1.6641. Min Range: -1.6641

Max Act: 1.3920. Min Act: -0.0000

Data Index: 251645 (C4 (Web Text))

Max Activating Token Index: 648

Text #16

Max Range: 1.6641. Min Range: -1.6641

Max Act: 1.2777. Min Act: -0.0000

Data Index: 461658 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 1.6641. Min Range: -1.6641

Max Act: 1.2946. Min Act: -0.0000

Data Index: 406879 (C4 (Web Text))

Max Activating Token Index: 773

Text #18

Max Range: 1.6641. Min Range: -1.6641

Max Act: 1.3951. Min Act: -0.0000

Data Index: 155943 (C4 (Web Text))

Max Activating Token Index: 198

Text #19

Max Range: 1.6641. Min Range: -1.6641

Max Act: 1.3084. Min Act: -0.0000

Data Index: 799573 (C4 (Web Text))

Max Activating Token Index: 917