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

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

Neuron 2284 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0643. Min Act: -0.0003

Data Index: 334270 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0645. Min Act: -0.0002

Data Index: 173193 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0638. Min Act: -0.0003

Data Index: 904591 (C4 (Web Text))

Max Activating Token Index: 181

Text #3

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0607. Min Act: -0.0003

Data Index: 961735 (C4 (Web Text))

Max Activating Token Index: 570

Text #4

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0600. Min Act: -0.0002

Data Index: 115566 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0592. Min Act: -0.0003

Data Index: 642472 (C4 (Web Text))

Max Activating Token Index: 385

Text #6

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0602. Min Act: -0.0003

Data Index: 732128 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0568. Min Act: -0.0003

Data Index: 406518 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0568. Min Act: -0.0002

Data Index: 1201252 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0575. Min Act: -0.0003

Data Index: 566757 (C4 (Web Text))

Max Activating Token Index: 325

Text #10

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0565. Min Act: -0.0003

Data Index: 815791 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0547. Min Act: -0.0003

Data Index: 634561 (C4 (Web Text))

Max Activating Token Index: 521

Text #12

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0562. Min Act: -0.0003

Data Index: 1146667 (C4 (Web Text))

Max Activating Token Index: 866

Text #13

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0536. Min Act: -0.0003

Data Index: 206791 (C4 (Web Text))

Max Activating Token Index: 103

Text #14

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0538. Min Act: -0.0003

Data Index: 868224 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0516. Min Act: -0.0003

Data Index: 519078 (C4 (Web Text))

Max Activating Token Index: 645

Text #16

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0528. Min Act: -0.0003

Data Index: 934285 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0501. Min Act: -0.0003

Data Index: 729594 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0495. Min Act: -0.0003

Data Index: 1341042 (C4 (Web Text))

Max Activating Token Index: 618

Text #19

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0514. Min Act: -0.0003

Data Index: 265515 (C4 (Web Text))

Max Activating Token Index: 227