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

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

Neuron 604 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0679. Min Act: -0.0005

Data Index: 167854 (C4 (Web Text))

Max Activating Token Index: 505

Text #1

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0645. Min Act: -0.0005

Data Index: 293614 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0579. Min Act: -0.0005

Data Index: 61281 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0621. Min Act: -0.0005

Data Index: 102908 (C4 (Web Text))

Max Activating Token Index: 831

Text #4

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0578. Min Act: -0.0005

Data Index: 1165778 (C4 (Web Text))

Max Activating Token Index: 357

Text #5

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0588. Min Act: -0.0005

Data Index: 1158254 (C4 (Web Text))

Max Activating Token Index: 239

Text #6

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0586. Min Act: -0.0005

Data Index: 68701 (C4 (Web Text))

Max Activating Token Index: 483

Text #7

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0583. Min Act: -0.0005

Data Index: 1253811 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0580. Min Act: -0.0005

Data Index: 233679 (C4 (Web Text))

Max Activating Token Index: 583

Text #9

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0567. Min Act: -0.0005

Data Index: 224346 (C4 (Web Text))

Max Activating Token Index: 616

Text #10

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0574. Min Act: -0.0005

Data Index: 530823 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0570. Min Act: -0.0005

Data Index: 186806 (C4 (Web Text))

Max Activating Token Index: 375

Text #12

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0556. Min Act: -0.0005

Data Index: 621051 (C4 (Web Text))

Max Activating Token Index: 851

Text #13

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0538. Min Act: -0.0005

Data Index: 849212 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0568. Min Act: -0.0005

Data Index: 1140789 (C4 (Web Text))

Max Activating Token Index: 626

Text #15

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0548. Min Act: -0.0005

Data Index: 238236 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0574. Min Act: -0.0005

Data Index: 1183537 (C4 (Web Text))

Max Activating Token Index: 810

Text #17

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0564. Min Act: -0.0005

Data Index: 96362 (C4 (Web Text))

Max Activating Token Index: 671

Text #18

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0534. Min Act: -0.0005

Data Index: 676676 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0555. Min Act: -0.0005

Data Index: 1128017 (C4 (Web Text))

Max Activating Token Index: 195