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

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

Neuron 844 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: 0.0560. Min Range: -0.0560

Max Act: 0.0559. Min Act: -0.0006

Data Index: 151051 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0560. Min Act: -0.0006

Data Index: 440632 (C4 (Web Text))

Max Activating Token Index: 921

Text #2

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0550. Min Act: -0.0006

Data Index: 591632 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0525. Min Act: -0.0006

Data Index: 1040855 (C4 (Web Text))

Max Activating Token Index: 845

Text #4

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0516. Min Act: -0.0006

Data Index: 169623 (C4 (Web Text))

Max Activating Token Index: 568

Text #5

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0525. Min Act: -0.0006

Data Index: 1028714 (C4 (Web Text))

Max Activating Token Index: 209

Text #6

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0510. Min Act: -0.0006

Data Index: 1150507 (C4 (Web Text))

Max Activating Token Index: 187

Text #7

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0515. Min Act: -0.0006

Data Index: 1257281 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0505. Min Act: -0.0006

Data Index: 1239281 (C4 (Web Text))

Max Activating Token Index: 742

Text #9

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0494. Min Act: -0.0006

Data Index: 676905 (C4 (Web Text))

Max Activating Token Index: 304

Text #10

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0508. Min Act: -0.0006

Data Index: 1247197 (C4 (Web Text))

Max Activating Token Index: 790

Text #11

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0521. Min Act: -0.0006

Data Index: 375410 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0448. Min Act: -0.0006

Data Index: 443182 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0495. Min Act: -0.0006

Data Index: 858865 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0482. Min Act: -0.0006

Data Index: 387347 (C4 (Web Text))

Max Activating Token Index: 234

Text #15

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0473. Min Act: -0.0006

Data Index: 678198 (C4 (Web Text))

Max Activating Token Index: 869

Text #16

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0488. Min Act: -0.0006

Data Index: 1137360 (C4 (Web Text))

Max Activating Token Index: 958

Text #17

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0468. Min Act: -0.0006

Data Index: 882380 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0471. Min Act: -0.0006

Data Index: 287492 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0466. Min Act: -0.0006

Data Index: 1143415 (C4 (Web Text))

Max Activating Token Index: 892