Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1977 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0688. Min Act: -0.0003

Data Index: 80933 (C4 (Web Text))

Max Activating Token Index: 1007

Text #1

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0654. Min Act: -0.0003

Data Index: 958649 (C4 (Web Text))

Max Activating Token Index: 99

Text #2

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0616. Min Act: -0.0002

Data Index: 671735 (C4 (Web Text))

Max Activating Token Index: 232

Text #3

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0605. Min Act: -0.0003

Data Index: 68097 (C4 (Web Text))

Max Activating Token Index: 206

Text #4

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0584. Min Act: -0.0003

Data Index: 330352 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0555. Min Act: -0.0003

Data Index: 1245172 (C4 (Web Text))

Max Activating Token Index: 640

Text #6

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0578. Min Act: -0.0002

Data Index: 1030831 (C4 (Web Text))

Max Activating Token Index: 552

Text #7

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0551. Min Act: -0.0003

Data Index: 597407 (C4 (Web Text))

Max Activating Token Index: 959

Text #8

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0566. Min Act: -0.0003

Data Index: 124016 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0571. Min Act: -0.0003

Data Index: 1302381 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0553. Min Act: -0.0003

Data Index: 1334302 (C4 (Web Text))

Max Activating Token Index: 864

Text #11

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0543. Min Act: -0.0003

Data Index: 160092 (C4 (Web Text))

Max Activating Token Index: 895

Text #12

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0556. Min Act: -0.0003

Data Index: 1042673 (C4 (Web Text))

Max Activating Token Index: 224

Text #13

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0525. Min Act: -0.0002

Data Index: 1120457 (C4 (Web Text))

Max Activating Token Index: 459

Text #14

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0538. Min Act: -0.0004

Data Index: 717064 (C4 (Web Text))

Max Activating Token Index: 523

Text #15

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0575. Min Act: -0.0003

Data Index: 1107060 (C4 (Web Text))

Max Activating Token Index: 560

Text #16

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0532. Min Act: -0.0003

Data Index: 340881 (C4 (Web Text))

Max Activating Token Index: 761

Text #17

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0535. Min Act: -0.0003

Data Index: 479767 (C4 (Web Text))

Max Activating Token Index: 558

Text #18

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0530. Min Act: -0.0003

Data Index: 555773 (C4 (Web Text))

Max Activating Token Index: 264

Text #19

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0525. Min Act: -0.0004

Data Index: 149790 (C4 (Web Text))

Max Activating Token Index: 243