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

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

Neuron 3758 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1240. Min Act: -0.0002

Data Index: 967523 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1282. Min Act: -0.0002

Data Index: 1054871 (C4 (Web Text))

Max Activating Token Index: 199

Text #2

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1182. Min Act: -0.0002

Data Index: 155350 (C4 (Web Text))

Max Activating Token Index: 279

Text #3

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1099. Min Act: -0.0002

Data Index: 809968 (C4 (Web Text))

Max Activating Token Index: 11

Text #4

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1060. Min Act: -0.0002

Data Index: 778364 (C4 (Web Text))

Max Activating Token Index: 364

Text #5

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1045. Min Act: -0.0002

Data Index: 137645 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1060. Min Act: -0.0002

Data Index: 504080 (C4 (Web Text))

Max Activating Token Index: 318

Text #7

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1052. Min Act: -0.0002

Data Index: 684459 (C4 (Web Text))

Max Activating Token Index: 773

Text #8

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1081. Min Act: -0.0002

Data Index: 54783 (C4 (Web Text))

Max Activating Token Index: 137

Text #9

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.0988. Min Act: -0.0002

Data Index: 933145 (C4 (Web Text))

Max Activating Token Index: 90

Text #10

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1014. Min Act: -0.0002

Data Index: 773983 (C4 (Web Text))

Max Activating Token Index: 346

Text #11

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1010. Min Act: -0.0002

Data Index: 1100496 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1002. Min Act: -0.0002

Data Index: 295258 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.0996. Min Act: -0.0002

Data Index: 91851 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.0957. Min Act: -0.0002

Data Index: 1256682 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.0983. Min Act: -0.0002

Data Index: 684634 (C4 (Web Text))

Max Activating Token Index: 16

Text #16

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.0966. Min Act: -0.0002

Data Index: 357278 (C4 (Web Text))

Max Activating Token Index: 628

Text #17

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.0952. Min Act: -0.0002

Data Index: 773455 (C4 (Web Text))

Max Activating Token Index: 578

Text #18

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.0942. Min Act: -0.0002

Data Index: 170203 (C4 (Web Text))

Max Activating Token Index: 1003

Text #19

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.0905. Min Act: -0.0002

Data Index: 783449 (C4 (Web Text))

Max Activating Token Index: 651