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

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

Neuron 340 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: 0.0621. Min Range: -0.0621

Max Act: 0.0621. Min Act: -0.0004

Data Index: 580778 (C4 (Web Text))

Max Activating Token Index: 660

Text #1

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0597. Min Act: -0.0003

Data Index: 233501 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0585. Min Act: -0.0004

Data Index: 26742 (C4 (Web Text))

Max Activating Token Index: 771

Text #3

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0548. Min Act: -0.0003

Data Index: 1290981 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0572. Min Act: -0.0003

Data Index: 234865 (C4 (Web Text))

Max Activating Token Index: 450

Text #5

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0547. Min Act: -0.0003

Data Index: 689120 (C4 (Web Text))

Max Activating Token Index: 535

Text #6

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0541. Min Act: -0.0003

Data Index: 518071 (C4 (Web Text))

Max Activating Token Index: 393

Text #7

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0538. Min Act: -0.0002

Data Index: 1341889 (C4 (Web Text))

Max Activating Token Index: 205

Text #8

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0538. Min Act: -0.0003

Data Index: 307225 (C4 (Web Text))

Max Activating Token Index: 750

Text #9

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0530. Min Act: -0.0003

Data Index: 934424 (C4 (Web Text))

Max Activating Token Index: 677

Text #10

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0545. Min Act: -0.0003

Data Index: 294352 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0544. Min Act: -0.0003

Data Index: 481849 (C4 (Web Text))

Max Activating Token Index: 390

Text #12

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0521. Min Act: -0.0003

Data Index: 824418 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0515. Min Act: -0.0003

Data Index: 61677 (C4 (Web Text))

Max Activating Token Index: 524

Text #14

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0514. Min Act: -0.0003

Data Index: 833427 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0512. Min Act: -0.0003

Data Index: 286884 (C4 (Web Text))

Max Activating Token Index: 525

Text #16

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0512. Min Act: -0.0004

Data Index: 278402 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0504. Min Act: -0.0003

Data Index: 203634 (C4 (Web Text))

Max Activating Token Index: 780

Text #18

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0520. Min Act: -0.0003

Data Index: 273182 (C4 (Web Text))

Max Activating Token Index: 983

Text #19

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0495. Min Act: -0.0003

Data Index: 886886 (C4 (Web Text))

Max Activating Token Index: 422