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

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

Neuron 591 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0118. Min Act: -0.0006

Data Index: 559800 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0104. Min Act: -0.0006

Data Index: 523529 (C4 (Web Text))

Max Activating Token Index: 441

Text #2

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0105. Min Act: -0.0006

Data Index: 949871 (C4 (Web Text))

Max Activating Token Index: 215

Text #3

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0107. Min Act: -0.0006

Data Index: 593479 (C4 (Web Text))

Max Activating Token Index: 937

Text #4

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0106. Min Act: -0.0006

Data Index: 224990 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0106. Min Act: -0.0006

Data Index: 1218510 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0099. Min Act: -0.0006

Data Index: 1340456 (C4 (Web Text))

Max Activating Token Index: 630

Text #7

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0103. Min Act: -0.0006

Data Index: 827451 (C4 (Web Text))

Max Activating Token Index: 853

Text #8

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0102. Min Act: -0.0006

Data Index: 476542 (C4 (Web Text))

Max Activating Token Index: 434

Text #9

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0103. Min Act: -0.0006

Data Index: 39659 (C4 (Web Text))

Max Activating Token Index: 354

Text #10

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0103. Min Act: -0.0006

Data Index: 420101 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0100. Min Act: -0.0006

Data Index: 64631 (C4 (Web Text))

Max Activating Token Index: 821

Text #12

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0102. Min Act: -0.0006

Data Index: 48275 (C4 (Web Text))

Max Activating Token Index: 663

Text #13

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0100. Min Act: -0.0006

Data Index: 1290890 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0100. Min Act: -0.0006

Data Index: 183342 (C4 (Web Text))

Max Activating Token Index: 1017

Text #15

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0096. Min Act: -0.0006

Data Index: 543550 (C4 (Web Text))

Max Activating Token Index: 553

Text #16

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0097. Min Act: -0.0006

Data Index: 384857 (C4 (Web Text))

Max Activating Token Index: 652

Text #17

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0099. Min Act: -0.0006

Data Index: 960556 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0098. Min Act: -0.0006

Data Index: 1045229 (C4 (Web Text))

Max Activating Token Index: 604

Text #19

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0098. Min Act: -0.0006

Data Index: 1287805 (C4 (Web Text))

Max Activating Token Index: 236