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

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

Neuron 2023 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: 0.0723. Min Range: -0.0723

Max Act: 0.0723. Min Act: -0.0003

Data Index: 95156 (C4 (Web Text))

Max Activating Token Index: 267

Text #1

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0699. Min Act: -0.0003

Data Index: 640254 (C4 (Web Text))

Max Activating Token Index: 613

Text #2

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0681. Min Act: -0.0003

Data Index: 1278292 (C4 (Web Text))

Max Activating Token Index: 616

Text #3

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0680. Min Act: -0.0003

Data Index: 720627 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0640. Min Act: -0.0003

Data Index: 950893 (C4 (Web Text))

Max Activating Token Index: 495

Text #5

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0654. Min Act: -0.0003

Data Index: 903116 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0611. Min Act: -0.0003

Data Index: 1353999 (C4 (Web Text))

Max Activating Token Index: 568

Text #7

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0603. Min Act: -0.0003

Data Index: 669558 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0632. Min Act: -0.0003

Data Index: 274277 (C4 (Web Text))

Max Activating Token Index: 992

Text #9

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0647. Min Act: -0.0002

Data Index: 122611 (C4 (Web Text))

Max Activating Token Index: 1003

Text #10

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0633. Min Act: -0.0004

Data Index: 1212394 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0620. Min Act: -0.0003

Data Index: 285111 (C4 (Web Text))

Max Activating Token Index: 467

Text #12

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0631. Min Act: -0.0003

Data Index: 675534 (C4 (Web Text))

Max Activating Token Index: 368

Text #13

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0609. Min Act: -0.0003

Data Index: 1185363 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0642. Min Act: -0.0003

Data Index: 712420 (C4 (Web Text))

Max Activating Token Index: 419

Text #15

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0612. Min Act: -0.0004

Data Index: 718856 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0623. Min Act: -0.0003

Data Index: 223956 (C4 (Web Text))

Max Activating Token Index: 366

Text #17

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0608. Min Act: -0.0003

Data Index: 4847 (C4 (Web Text))

Max Activating Token Index: 743

Text #18

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0671. Min Act: -0.0003

Data Index: 472519 (C4 (Web Text))

Max Activating Token Index: 477

Text #19

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0633. Min Act: -0.0003

Data Index: 958561 (C4 (Web Text))

Max Activating Token Index: 393