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

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

Neuron 2489 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.6032. Min Act: -0.0000

Data Index: 414994 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.5312. Min Act: -0.0000

Data Index: 647987 (C4 (Web Text))

Max Activating Token Index: 293

Text #2

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.5012. Min Act: -0.0000

Data Index: 537982 (C4 (Web Text))

Max Activating Token Index: 782

Text #3

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.4948. Min Act: -0.0000

Data Index: 313118 (C4 (Web Text))

Max Activating Token Index: 671

Text #4

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.4867. Min Act: 0.0000

Data Index: 427374 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.4811. Min Act: -0.0000

Data Index: 1180705 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.4787. Min Act: -0.0000

Data Index: 1353177 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.4683. Min Act: -0.0000

Data Index: 702458 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.4479. Min Act: -0.0000

Data Index: 140011 (C4 (Web Text))

Max Activating Token Index: 743

Text #9

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.4597. Min Act: -0.0000

Data Index: 1276297 (C4 (Web Text))

Max Activating Token Index: 772

Text #10

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.4579. Min Act: -0.0000

Data Index: 150548 (C4 (Web Text))

Max Activating Token Index: 130

Text #11

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.4544. Min Act: -0.0000

Data Index: 433939 (C4 (Web Text))

Max Activating Token Index: 85

Text #12

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.4515. Min Act: -0.0000

Data Index: 1132604 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.4239. Min Act: -0.0000

Data Index: 102919 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.4476. Min Act: -0.0000

Data Index: 1139847 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.4477. Min Act: -0.0000

Data Index: 387588 (C4 (Web Text))

Max Activating Token Index: 897

Text #16

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.4420. Min Act: -0.0000

Data Index: 1100638 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.4542. Min Act: -0.0000

Data Index: 731620 (C4 (Web Text))

Max Activating Token Index: 580

Text #18

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.4561. Min Act: -0.0000

Data Index: 1118766 (C4 (Web Text))

Max Activating Token Index: 1022

Text #19

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.4390. Min Act: -0.0000

Data Index: 324377 (C4 (Web Text))

Max Activating Token Index: 388