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

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

Neuron 4448 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: 3.1318. Min Range: -3.1318

Max Act: 3.0404. Min Act: -0.0000

Data Index: 372393 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 3.1318. Min Range: -3.1318

Max Act: 3.1318. Min Act: -0.0000

Data Index: 783785 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 3.1318. Min Range: -3.1318

Max Act: 2.6914. Min Act: -0.0000

Data Index: 256664 (C4 (Web Text))

Max Activating Token Index: 1002

Text #3

Max Range: 3.1318. Min Range: -3.1318

Max Act: 2.5865. Min Act: -0.0000

Data Index: 245632 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 3.1318. Min Range: -3.1318

Max Act: 2.5089. Min Act: -0.0000

Data Index: 1318306 (C4 (Web Text))

Max Activating Token Index: 722

Text #5

Max Range: 3.1318. Min Range: -3.1318

Max Act: 2.6541. Min Act: -0.0000

Data Index: 681224 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 3.1318. Min Range: -3.1318

Max Act: 2.4885. Min Act: -0.0000

Data Index: 394141 (C4 (Web Text))

Max Activating Token Index: 3

Text #7

Max Range: 3.1318. Min Range: -3.1318

Max Act: 2.4755. Min Act: -0.0000

Data Index: 1084041 (C4 (Web Text))

Max Activating Token Index: 910

Text #8

Max Range: 3.1318. Min Range: -3.1318

Max Act: 2.6057. Min Act: -0.0000

Data Index: 702251 (C4 (Web Text))

Max Activating Token Index: 760

Text #9

Max Range: 3.1318. Min Range: -3.1318

Max Act: 2.4464. Min Act: -0.0000

Data Index: 515301 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 3.1318. Min Range: -3.1318

Max Act: 2.4218. Min Act: -0.0000

Data Index: 273955 (C4 (Web Text))

Max Activating Token Index: 990

Text #11

Max Range: 3.1318. Min Range: -3.1318

Max Act: 2.4130. Min Act: -0.0000

Data Index: 1254720 (C4 (Web Text))

Max Activating Token Index: 213

Text #12

Max Range: 3.1318. Min Range: -3.1318

Max Act: 2.2927. Min Act: -0.0000

Data Index: 630518 (C4 (Web Text))

Max Activating Token Index: 200

Text #13

Max Range: 3.1318. Min Range: -3.1318

Max Act: 2.4087. Min Act: -0.0000

Data Index: 1225918 (C4 (Web Text))

Max Activating Token Index: 89

Text #14

Max Range: 3.1318. Min Range: -3.1318

Max Act: 2.1327. Min Act: -0.0000

Data Index: 50064 (C4 (Web Text))

Max Activating Token Index: 892

Text #15

Max Range: 3.1318. Min Range: -3.1318

Max Act: 2.2497. Min Act: -0.0000

Data Index: 751741 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 3.1318. Min Range: -3.1318

Max Act: 2.2431. Min Act: -0.0000

Data Index: 577340 (C4 (Web Text))

Max Activating Token Index: 531

Text #17

Max Range: 3.1318. Min Range: -3.1318

Max Act: 2.4757. Min Act: -0.0000

Data Index: 584240 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 3.1318. Min Range: -3.1318

Max Act: 1.9942. Min Act: -0.0000

Data Index: 406601 (C4 (Web Text))

Max Activating Token Index: 335

Text #19

Max Range: 3.1318. Min Range: -3.1318

Max Act: 2.2048. Min Act: -0.0000

Data Index: 286430 (C4 (Web Text))

Max Activating Token Index: 13