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

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

Neuron 1816 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0478. Min Act: -0.0002

Data Index: 1266149 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0476. Min Act: -0.0002

Data Index: 830298 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0474. Min Act: -0.0002

Data Index: 906459 (C4 (Web Text))

Max Activating Token Index: 439

Text #3

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0473. Min Act: -0.0002

Data Index: 102091 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0469. Min Act: -0.0002

Data Index: 1198487 (C4 (Web Text))

Max Activating Token Index: 108

Text #5

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0469. Min Act: -0.0002

Data Index: 435392 (C4 (Web Text))

Max Activating Token Index: 385

Text #6

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0468. Min Act: -0.0002

Data Index: 1057317 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0458. Min Act: -0.0002

Data Index: 604081 (C4 (Web Text))

Max Activating Token Index: 447

Text #8

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0466. Min Act: -0.0002

Data Index: 717896 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0465. Min Act: -0.0002

Data Index: 1128863 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0464. Min Act: -0.0002

Data Index: 681051 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0473. Min Act: -0.0002

Data Index: 1094583 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0462. Min Act: -0.0002

Data Index: 456680 (C4 (Web Text))

Max Activating Token Index: 425

Text #13

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0452. Min Act: -0.0002

Data Index: 1232895 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0461. Min Act: -0.0002

Data Index: 89995 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0460. Min Act: -0.0002

Data Index: 330762 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0459. Min Act: -0.0002

Data Index: 1238036 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0458. Min Act: -0.0002

Data Index: 157746 (C4 (Web Text))

Max Activating Token Index: 607

Text #18

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0449. Min Act: -0.0002

Data Index: 635372 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0458. Min Act: -0.0002

Data Index: 1349528 (C4 (Web Text))

Max Activating Token Index: 26