Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1852 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0935. Min Act: -0.0003

Data Index: 227385 (C4 (Web Text))

Max Activating Token Index: 696

Text #1

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0837. Min Act: -0.0003

Data Index: 513329 (C4 (Web Text))

Max Activating Token Index: 504

Text #2

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0754. Min Act: -0.0003

Data Index: 1282460 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0743. Min Act: -0.0002

Data Index: 624681 (C4 (Web Text))

Max Activating Token Index: 862

Text #4

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0717. Min Act: -0.0002

Data Index: 194090 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0714. Min Act: -0.0003

Data Index: 348292 (C4 (Web Text))

Max Activating Token Index: 221

Text #6

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0712. Min Act: -0.0003

Data Index: 878505 (C4 (Web Text))

Max Activating Token Index: 275

Text #7

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0701. Min Act: -0.0003

Data Index: 769474 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0729. Min Act: -0.0003

Data Index: 1108435 (C4 (Web Text))

Max Activating Token Index: 278

Text #9

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0693. Min Act: -0.0003

Data Index: 995420 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0694. Min Act: -0.0003

Data Index: 1346696 (C4 (Web Text))

Max Activating Token Index: 288

Text #11

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0695. Min Act: -0.0003

Data Index: 1016887 (C4 (Web Text))

Max Activating Token Index: 909

Text #12

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0694. Min Act: -0.0004

Data Index: 259479 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0694. Min Act: -0.0003

Data Index: 957616 (C4 (Web Text))

Max Activating Token Index: 666

Text #14

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0680. Min Act: -0.0003

Data Index: 161531 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0676. Min Act: -0.0003

Data Index: 6851 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0675. Min Act: -0.0002

Data Index: 647972 (C4 (Web Text))

Max Activating Token Index: 567

Text #17

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0693. Min Act: -0.0003

Data Index: 1230070 (C4 (Web Text))

Max Activating Token Index: 228

Text #18

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0677. Min Act: -0.0003

Data Index: 299212 (C4 (Web Text))

Max Activating Token Index: 432

Text #19

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0667. Min Act: -0.0004

Data Index: 1230232 (C4 (Web Text))

Max Activating Token Index: 865