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

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

Neuron 590 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0727. Min Act: -0.0002

Data Index: 43965 (C4 (Web Text))

Max Activating Token Index: 766

Text #1

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0658. Min Act: -0.0002

Data Index: 713447 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0583. Min Act: -0.0002

Data Index: 39460 (C4 (Web Text))

Max Activating Token Index: 568

Text #3

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0606. Min Act: -0.0002

Data Index: 595214 (C4 (Web Text))

Max Activating Token Index: 673

Text #4

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0577. Min Act: -0.0002

Data Index: 866278 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0596. Min Act: -0.0002

Data Index: 749495 (C4 (Web Text))

Max Activating Token Index: 745

Text #6

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0583. Min Act: -0.0002

Data Index: 1221816 (C4 (Web Text))

Max Activating Token Index: 349

Text #7

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0570. Min Act: -0.0002

Data Index: 411968 (C4 (Web Text))

Max Activating Token Index: 502

Text #8

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0549. Min Act: -0.0002

Data Index: 366436 (C4 (Web Text))

Max Activating Token Index: 330

Text #9

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0544. Min Act: -0.0002

Data Index: 729009 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0536. Min Act: -0.0002

Data Index: 1260630 (C4 (Web Text))

Max Activating Token Index: 374

Text #11

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0511. Min Act: -0.0002

Data Index: 1258209 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0514. Min Act: -0.0002

Data Index: 732415 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0520. Min Act: -0.0002

Data Index: 183540 (C4 (Web Text))

Max Activating Token Index: 292

Text #14

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0513. Min Act: -0.0002

Data Index: 796271 (C4 (Web Text))

Max Activating Token Index: 225

Text #15

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0539. Min Act: -0.0002

Data Index: 345960 (C4 (Web Text))

Max Activating Token Index: 340

Text #16

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0475. Min Act: -0.0002

Data Index: 968277 (C4 (Web Text))

Max Activating Token Index: 715

Text #17

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0514. Min Act: -0.0002

Data Index: 549703 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0470. Min Act: -0.0002

Data Index: 562896 (C4 (Web Text))

Max Activating Token Index: 184

Text #19

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0505. Min Act: -0.0002

Data Index: 442144 (C4 (Web Text))

Max Activating Token Index: 761