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

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

Neuron 861 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0606. Min Act: -0.0002

Data Index: 118030 (C4 (Web Text))

Max Activating Token Index: 393

Text #1

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0611. Min Act: -0.0002

Data Index: 731873 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0570. Min Act: -0.0001

Data Index: 1142609 (C4 (Web Text))

Max Activating Token Index: 795

Text #3

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0577. Min Act: -0.0002

Data Index: 622974 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0564. Min Act: -0.0002

Data Index: 878879 (C4 (Web Text))

Max Activating Token Index: 352

Text #5

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0592. Min Act: -0.0001

Data Index: 599568 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0546. Min Act: -0.0002

Data Index: 517592 (C4 (Web Text))

Max Activating Token Index: 349

Text #7

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0545. Min Act: -0.0001

Data Index: 1215607 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0552. Min Act: -0.0002

Data Index: 365374 (C4 (Web Text))

Max Activating Token Index: 384

Text #9

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0542. Min Act: -0.0002

Data Index: 266031 (C4 (Web Text))

Max Activating Token Index: 509

Text #10

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0521. Min Act: -0.0002

Data Index: 394081 (C4 (Web Text))

Max Activating Token Index: 805

Text #11

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0541. Min Act: -0.0002

Data Index: 112359 (C4 (Web Text))

Max Activating Token Index: 265

Text #12

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0529. Min Act: -0.0002

Data Index: 789130 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0546. Min Act: -0.0002

Data Index: 909898 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0523. Min Act: -0.0002

Data Index: 636639 (C4 (Web Text))

Max Activating Token Index: 284

Text #15

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0523. Min Act: -0.0001

Data Index: 1104219 (C4 (Web Text))

Max Activating Token Index: 728

Text #16

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0519. Min Act: -0.0001

Data Index: 119692 (C4 (Web Text))

Max Activating Token Index: 913

Text #17

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0527. Min Act: -0.0002

Data Index: 786727 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0496. Min Act: -0.0001

Data Index: 203515 (C4 (Web Text))

Max Activating Token Index: 624

Text #19

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0500. Min Act: -0.0002

Data Index: 468865 (C4 (Web Text))

Max Activating Token Index: 413