Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 192 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0554. Min Act: -0.0006

Data Index: 276141 (C4 (Web Text))

Max Activating Token Index: 912

Text #1

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0587. Min Act: -0.0006

Data Index: 1015638 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0571. Min Act: -0.0006

Data Index: 1337816 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0576. Min Act: -0.0006

Data Index: 380989 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0552. Min Act: -0.0006

Data Index: 262414 (C4 (Web Text))

Max Activating Token Index: 75

Text #5

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0557. Min Act: -0.0006

Data Index: 1358087 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0555. Min Act: -0.0006

Data Index: 1355360 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0530. Min Act: -0.0006

Data Index: 1252705 (C4 (Web Text))

Max Activating Token Index: 697

Text #8

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0562. Min Act: -0.0006

Data Index: 1050511 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0559. Min Act: -0.0006

Data Index: 1217533 (C4 (Web Text))

Max Activating Token Index: 698

Text #10

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0506. Min Act: -0.0006

Data Index: 811364 (C4 (Web Text))

Max Activating Token Index: 713

Text #11

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0549. Min Act: -0.0006

Data Index: 630704 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0535. Min Act: -0.0006

Data Index: 73346 (C4 (Web Text))

Max Activating Token Index: 293

Text #13

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0567. Min Act: -0.0006

Data Index: 1003252 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0578. Min Act: -0.0006

Data Index: 466365 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0553. Min Act: -0.0006

Data Index: 557100 (C4 (Web Text))

Max Activating Token Index: 47

Text #16

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0576. Min Act: -0.0006

Data Index: 446261 (C4 (Web Text))

Max Activating Token Index: 546

Text #17

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0553. Min Act: -0.0006

Data Index: 1043330 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0573. Min Act: -0.0006

Data Index: 50227 (C4 (Web Text))

Max Activating Token Index: 88

Text #19

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0562. Min Act: -0.0006

Data Index: 184124 (C4 (Web Text))

Max Activating Token Index: 497