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

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

Neuron 789 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0762. Min Act: -0.0002

Data Index: 120531 (C4 (Web Text))

Max Activating Token Index: 540

Text #1

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0679. Min Act: -0.0002

Data Index: 869234 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0616. Min Act: -0.0002

Data Index: 199146 (C4 (Web Text))

Max Activating Token Index: 534

Text #3

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0613. Min Act: -0.0002

Data Index: 604518 (C4 (Web Text))

Max Activating Token Index: 477

Text #4

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0663. Min Act: -0.0002

Data Index: 1188613 (C4 (Web Text))

Max Activating Token Index: 276

Text #5

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0579. Min Act: -0.0002

Data Index: 1210857 (C4 (Web Text))

Max Activating Token Index: 922

Text #6

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0614. Min Act: -0.0002

Data Index: 1194912 (C4 (Web Text))

Max Activating Token Index: 419

Text #7

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0634. Min Act: -0.0002

Data Index: 1218688 (C4 (Web Text))

Max Activating Token Index: 318

Text #8

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0610. Min Act: -0.0002

Data Index: 1179100 (C4 (Web Text))

Max Activating Token Index: 369

Text #9

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0630. Min Act: -0.0002

Data Index: 556779 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0602. Min Act: -0.0002

Data Index: 495014 (C4 (Web Text))

Max Activating Token Index: 264

Text #11

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0603. Min Act: -0.0002

Data Index: 113953 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0574. Min Act: -0.0002

Data Index: 982172 (C4 (Web Text))

Max Activating Token Index: 974

Text #13

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0567. Min Act: -0.0002

Data Index: 54239 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0591. Min Act: -0.0002

Data Index: 1334518 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0546. Min Act: -0.0002

Data Index: 475598 (C4 (Web Text))

Max Activating Token Index: 974

Text #16

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0577. Min Act: -0.0002

Data Index: 320409 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0464. Min Act: -0.0002

Data Index: 1071169 (C4 (Web Text))

Max Activating Token Index: 628

Text #18

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0576. Min Act: -0.0002

Data Index: 34843 (C4 (Web Text))

Max Activating Token Index: 497

Text #19

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0531. Min Act: -0.0002

Data Index: 863012 (C4 (Web Text))

Max Activating Token Index: 508