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

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

Neuron 3331 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4033. Min Range: -1.4033

Max Act: 1.4033. Min Act: -0.0000

Data Index: 1149797 (C4 (Web Text))

Max Activating Token Index: 556

Text #1

Max Range: 1.4033. Min Range: -1.4033

Max Act: 1.3579. Min Act: -0.0000

Data Index: 948656 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 1.4033. Min Range: -1.4033

Max Act: 1.1591. Min Act: -0.0000

Data Index: 1175565 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 1.4033. Min Range: -1.4033

Max Act: 1.1268. Min Act: -0.0000

Data Index: 964755 (C4 (Web Text))

Max Activating Token Index: 814

Text #4

Max Range: 1.4033. Min Range: -1.4033

Max Act: 1.0910. Min Act: -0.0000

Data Index: 248987 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 1.4033. Min Range: -1.4033

Max Act: 1.0458. Min Act: -0.0000

Data Index: 991053 (C4 (Web Text))

Max Activating Token Index: 588

Text #6

Max Range: 1.4033. Min Range: -1.4033

Max Act: 1.0308. Min Act: -0.0000

Data Index: 531293 (C4 (Web Text))

Max Activating Token Index: 3

Text #7

Max Range: 1.4033. Min Range: -1.4033

Max Act: 0.9029. Min Act: -0.0000

Data Index: 360542 (C4 (Web Text))

Max Activating Token Index: 115

Text #8

Max Range: 1.4033. Min Range: -1.4033

Max Act: 0.8834. Min Act: -0.0000

Data Index: 369095 (C4 (Web Text))

Max Activating Token Index: 382

Text #9

Max Range: 1.4033. Min Range: -1.4033

Max Act: 0.9144. Min Act: -0.0001

Data Index: 296729 (C4 (Web Text))

Max Activating Token Index: 377

Text #10

Max Range: 1.4033. Min Range: -1.4033

Max Act: 0.9449. Min Act: -0.0000

Data Index: 1336589 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 1.4033. Min Range: -1.4033

Max Act: 0.9426. Min Act: -0.0000

Data Index: 139531 (C4 (Web Text))

Max Activating Token Index: 2

Text #12

Max Range: 1.4033. Min Range: -1.4033

Max Act: 0.9476. Min Act: -0.0000

Data Index: 613584 (C4 (Web Text))

Max Activating Token Index: 176

Text #13

Max Range: 1.4033. Min Range: -1.4033

Max Act: 0.9143. Min Act: -0.0000

Data Index: 575702 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 1.4033. Min Range: -1.4033

Max Act: 0.9102. Min Act: -0.0000

Data Index: 1238299 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 1.4033. Min Range: -1.4033

Max Act: 0.9237. Min Act: -0.0000

Data Index: 1299040 (C4 (Web Text))

Max Activating Token Index: 238

Text #16

Max Range: 1.4033. Min Range: -1.4033

Max Act: 0.8889. Min Act: -0.0000

Data Index: 905737 (C4 (Web Text))

Max Activating Token Index: 651

Text #17

Max Range: 1.4033. Min Range: -1.4033

Max Act: 0.8642. Min Act: -0.0000

Data Index: 1007199 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 1.4033. Min Range: -1.4033

Max Act: 0.8535. Min Act: -0.0001

Data Index: 262610 (C4 (Web Text))

Max Activating Token Index: 645

Text #19

Max Range: 1.4033. Min Range: -1.4033

Max Act: 0.8503. Min Act: -0.0000

Data Index: 811174 (C4 (Web Text))

Max Activating Token Index: 621