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

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

Neuron 1330 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: 0.0734. Min Range: -0.0734

Max Act: 0.0702. Min Act: -0.0003

Data Index: 41443 (C4 (Web Text))

Max Activating Token Index: 699

Text #1

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0734. Min Act: -0.0003

Data Index: 1180565 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0666. Min Act: -0.0002

Data Index: 242223 (C4 (Web Text))

Max Activating Token Index: 584

Text #3

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0678. Min Act: -0.0003

Data Index: 216290 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0637. Min Act: -0.0003

Data Index: 207522 (C4 (Web Text))

Max Activating Token Index: 322

Text #5

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0627. Min Act: -0.0003

Data Index: 716937 (C4 (Web Text))

Max Activating Token Index: 297

Text #6

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0602. Min Act: -0.0003

Data Index: 151211 (C4 (Web Text))

Max Activating Token Index: 651

Text #7

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0634. Min Act: -0.0003

Data Index: 1288204 (C4 (Web Text))

Max Activating Token Index: 471

Text #8

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0603. Min Act: -0.0003

Data Index: 579254 (C4 (Web Text))

Max Activating Token Index: 787

Text #9

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0639. Min Act: -0.0003

Data Index: 609550 (C4 (Web Text))

Max Activating Token Index: 503

Text #10

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0608. Min Act: -0.0003

Data Index: 217637 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0587. Min Act: -0.0003

Data Index: 913078 (C4 (Web Text))

Max Activating Token Index: 853

Text #12

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0577. Min Act: -0.0003

Data Index: 1042553 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0578. Min Act: -0.0004

Data Index: 646701 (C4 (Web Text))

Max Activating Token Index: 909

Text #14

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0551. Min Act: -0.0003

Data Index: 1031793 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0551. Min Act: -0.0004

Data Index: 84960 (C4 (Web Text))

Max Activating Token Index: 542

Text #16

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0567. Min Act: -0.0004

Data Index: 1280 (C4 (Web Text))

Max Activating Token Index: 241

Text #17

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0569. Min Act: -0.0003

Data Index: 1158338 (C4 (Web Text))

Max Activating Token Index: 367

Text #18

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0529. Min Act: -0.0003

Data Index: 224083 (C4 (Web Text))

Max Activating Token Index: 668

Text #19

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0549. Min Act: -0.0003

Data Index: 342618 (C4 (Web Text))

Max Activating Token Index: 54