Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2017 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.6016. Min Act: -0.0000

Data Index: 968770 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.5662. Min Act: -0.0000

Data Index: 915353 (C4 (Web Text))

Max Activating Token Index: 373

Text #2

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.4420. Min Act: -0.0000

Data Index: 822332 (C4 (Web Text))

Max Activating Token Index: 633

Text #3

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.4735. Min Act: -0.0000

Data Index: 631294 (C4 (Web Text))

Max Activating Token Index: 594

Text #4

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.4511. Min Act: -0.0000

Data Index: 885989 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.3663. Min Act: -0.0000

Data Index: 1107006 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.3346. Min Act: -0.0000

Data Index: 591416 (C4 (Web Text))

Max Activating Token Index: 868

Text #7

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.2992. Min Act: -0.0000

Data Index: 1053033 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.2938. Min Act: -0.0000

Data Index: 1215968 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.2874. Min Act: -0.0000

Data Index: 412383 (C4 (Web Text))

Max Activating Token Index: 573

Text #10

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.2767. Min Act: -0.0000

Data Index: 1115261 (C4 (Web Text))

Max Activating Token Index: 262

Text #11

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.2648. Min Act: -0.0000

Data Index: 3670 (C4 (Web Text))

Max Activating Token Index: 379

Text #12

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.2510. Min Act: -0.0000

Data Index: 1238230 (C4 (Web Text))

Max Activating Token Index: 365

Text #13

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.2695. Min Act: -0.0000

Data Index: 1083392 (C4 (Web Text))

Max Activating Token Index: 218

Text #14

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.2511. Min Act: -0.0000

Data Index: 389655 (C4 (Web Text))

Max Activating Token Index: 753

Text #15

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.2669. Min Act: -0.0000

Data Index: 1060329 (C4 (Web Text))

Max Activating Token Index: 44

Text #16

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.2650. Min Act: -0.0000

Data Index: 1157295 (C4 (Web Text))

Max Activating Token Index: 570

Text #17

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.2616. Min Act: 0.0000

Data Index: 270712 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.2552. Min Act: -0.0000

Data Index: 910311 (C4 (Web Text))

Max Activating Token Index: 787

Text #19

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.2517. Min Act: -0.0000

Data Index: 422150 (C4 (Web Text))

Max Activating Token Index: 507