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

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

Neuron 1558 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: 0.0648. Min Range: -0.0648

Max Act: 0.0648. Min Act: -0.0004

Data Index: 878703 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0643. Min Act: -0.0003

Data Index: 725628 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0595. Min Act: -0.0004

Data Index: 204841 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0562. Min Act: -0.0003

Data Index: 997630 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0574. Min Act: -0.0003

Data Index: 1120504 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0563. Min Act: -0.0004

Data Index: 213210 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0565. Min Act: -0.0003

Data Index: 505410 (C4 (Web Text))

Max Activating Token Index: 599

Text #7

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0557. Min Act: -0.0003

Data Index: 27681 (C4 (Web Text))

Max Activating Token Index: 173

Text #8

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0518. Min Act: -0.0003

Data Index: 313680 (C4 (Web Text))

Max Activating Token Index: 701

Text #9

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0547. Min Act: -0.0003

Data Index: 536056 (C4 (Web Text))

Max Activating Token Index: 576

Text #10

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0549. Min Act: -0.0003

Data Index: 1235772 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0530. Min Act: -0.0004

Data Index: 1029459 (C4 (Web Text))

Max Activating Token Index: 520

Text #12

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0595. Min Act: -0.0002

Data Index: 126278 (C4 (Web Text))

Max Activating Token Index: 370

Text #13

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0539. Min Act: -0.0004

Data Index: 1206354 (C4 (Web Text))

Max Activating Token Index: 625

Text #14

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0548. Min Act: -0.0003

Data Index: 314490 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0495. Min Act: -0.0003

Data Index: 809939 (C4 (Web Text))

Max Activating Token Index: 786

Text #16

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0522. Min Act: -0.0003

Data Index: 218512 (C4 (Web Text))

Max Activating Token Index: 741

Text #17

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0535. Min Act: -0.0003

Data Index: 1286754 (C4 (Web Text))

Max Activating Token Index: 567

Text #18

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0543. Min Act: -0.0004

Data Index: 1157388 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0529. Min Act: -0.0004

Data Index: 1005964 (C4 (Web Text))

Max Activating Token Index: 608