Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5000 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0552. Min Act: -0.0002

Data Index: 70032 (C4 (Web Text))

Max Activating Token Index: 345

Text #1

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0552. Min Act: -0.0002

Data Index: 931582 (C4 (Web Text))

Max Activating Token Index: 625

Text #2

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0558. Min Act: -0.0002

Data Index: 1203549 (C4 (Web Text))

Max Activating Token Index: 538

Text #3

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0557. Min Act: -0.0002

Data Index: 2001 (C4 (Web Text))

Max Activating Token Index: 63

Text #4

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0557. Min Act: -0.0002

Data Index: 269873 (C4 (Web Text))

Max Activating Token Index: 258

Text #5

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0540. Min Act: -0.0002

Data Index: 926519 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0540. Min Act: -0.0002

Data Index: 790099 (C4 (Web Text))

Max Activating Token Index: 648

Text #7

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0539. Min Act: -0.0002

Data Index: 721734 (C4 (Web Text))

Max Activating Token Index: 205

Text #8

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0542. Min Act: -0.0002

Data Index: 1118904 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0542. Min Act: -0.0002

Data Index: 408379 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0547. Min Act: -0.0002

Data Index: 926215 (C4 (Web Text))

Max Activating Token Index: 522

Text #11

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0538. Min Act: -0.0002

Data Index: 598396 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0536. Min Act: -0.0002

Data Index: 885365 (C4 (Web Text))

Max Activating Token Index: 209

Text #13

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0539. Min Act: -0.0002

Data Index: 847622 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0524. Min Act: -0.0002

Data Index: 33123 (C4 (Web Text))

Max Activating Token Index: 221

Text #15

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0518. Min Act: -0.0002

Data Index: 498390 (C4 (Web Text))

Max Activating Token Index: 370

Text #16

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0529. Min Act: -0.0002

Data Index: 410929 (C4 (Web Text))

Max Activating Token Index: 731

Text #17

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0518. Min Act: -0.0002

Data Index: 864210 (C4 (Web Text))

Max Activating Token Index: 726

Text #18

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0531. Min Act: -0.0002

Data Index: 1067666 (C4 (Web Text))

Max Activating Token Index: 723

Text #19

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0528. Min Act: -0.0002

Data Index: 456967 (C4 (Web Text))

Max Activating Token Index: 612