Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3201 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.4663. Min Act: -0.0003

Data Index: 762483 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.4462. Min Act: -0.0003

Data Index: 1000655 (C4 (Web Text))

Max Activating Token Index: 770

Text #2

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.4312. Min Act: -0.0003

Data Index: 777199 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.4260. Min Act: -0.0003

Data Index: 630758 (C4 (Web Text))

Max Activating Token Index: 847

Text #4

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3959. Min Act: -0.0003

Data Index: 843306 (C4 (Web Text))

Max Activating Token Index: 277

Text #5

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3742. Min Act: -0.0003

Data Index: 815454 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3936. Min Act: -0.0003

Data Index: 636832 (C4 (Web Text))

Max Activating Token Index: 482

Text #7

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3713. Min Act: -0.0003

Data Index: 555898 (C4 (Web Text))

Max Activating Token Index: 537

Text #8

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3841. Min Act: -0.0003

Data Index: 1217732 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3796. Min Act: -0.0003

Data Index: 86581 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3672. Min Act: -0.0003

Data Index: 1041648 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3683. Min Act: -0.0003

Data Index: 1237096 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3506. Min Act: -0.0003

Data Index: 781970 (C4 (Web Text))

Max Activating Token Index: 190

Text #13

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3732. Min Act: -0.0003

Data Index: 485842 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3559. Min Act: -0.0003

Data Index: 604187 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3559. Min Act: -0.0003

Data Index: 1336796 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3459. Min Act: -0.0003

Data Index: 482993 (C4 (Web Text))

Max Activating Token Index: 343

Text #17

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3459. Min Act: -0.0003

Data Index: 1084317 (C4 (Web Text))

Max Activating Token Index: 267

Text #18

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3451. Min Act: -0.0003

Data Index: 127694 (C4 (Web Text))

Max Activating Token Index: 425

Text #19

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3134. Min Act: -0.0003

Data Index: 1073780 (C4 (Web Text))

Max Activating Token Index: 557