Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1422 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0687. Min Act: -0.0003

Data Index: 401294 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0628. Min Act: -0.0003

Data Index: 625254 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0605. Min Act: -0.0003

Data Index: 1332611 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0631. Min Act: -0.0003

Data Index: 69436 (C4 (Web Text))

Max Activating Token Index: 434

Text #4

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0630. Min Act: -0.0003

Data Index: 392648 (C4 (Web Text))

Max Activating Token Index: 640

Text #5

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0578. Min Act: -0.0003

Data Index: 1323403 (C4 (Web Text))

Max Activating Token Index: 271

Text #6

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0641. Min Act: -0.0003

Data Index: 1019958 (C4 (Web Text))

Max Activating Token Index: 717

Text #7

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0574. Min Act: -0.0003

Data Index: 126421 (C4 (Web Text))

Max Activating Token Index: 392

Text #8

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0595. Min Act: -0.0003

Data Index: 1089134 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0553. Min Act: -0.0003

Data Index: 1194485 (C4 (Web Text))

Max Activating Token Index: 646

Text #10

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0633. Min Act: -0.0003

Data Index: 244183 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0592. Min Act: -0.0003

Data Index: 1878 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0605. Min Act: -0.0003

Data Index: 1119264 (C4 (Web Text))

Max Activating Token Index: 58

Text #13

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0530. Min Act: -0.0003

Data Index: 1059214 (C4 (Web Text))

Max Activating Token Index: 581

Text #14

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0507. Min Act: -0.0003

Data Index: 1290404 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0552. Min Act: -0.0003

Data Index: 692421 (C4 (Web Text))

Max Activating Token Index: 149

Text #16

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0551. Min Act: -0.0003

Data Index: 1183423 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0581. Min Act: -0.0003

Data Index: 101430 (C4 (Web Text))

Max Activating Token Index: 992

Text #18

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0541. Min Act: -0.0003

Data Index: 1055542 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0553. Min Act: -0.0003

Data Index: 1330313 (C4 (Web Text))

Max Activating Token Index: 194