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

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

Neuron 4546 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0717. Min Act: -0.0001

Data Index: 56083 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0661. Min Act: -0.0001

Data Index: 577893 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0713. Min Act: -0.0001

Data Index: 493498 (C4 (Web Text))

Max Activating Token Index: 450

Text #3

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0625. Min Act: -0.0001

Data Index: 538324 (C4 (Web Text))

Max Activating Token Index: 774

Text #4

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0699. Min Act: -0.0001

Data Index: 687723 (C4 (Web Text))

Max Activating Token Index: 980

Text #5

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0644. Min Act: -0.0001

Data Index: 1328536 (C4 (Web Text))

Max Activating Token Index: 868

Text #6

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0598. Min Act: -0.0001

Data Index: 856079 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0497. Min Act: -0.0001

Data Index: 765339 (C4 (Web Text))

Max Activating Token Index: 57

Text #8

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0590. Min Act: -0.0001

Data Index: 631877 (C4 (Web Text))

Max Activating Token Index: 966

Text #9

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0520. Min Act: -0.0001

Data Index: 153769 (C4 (Web Text))

Max Activating Token Index: 184

Text #10

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0551. Min Act: -0.0001

Data Index: 594506 (C4 (Web Text))

Max Activating Token Index: 876

Text #11

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0510. Min Act: -0.0001

Data Index: 636483 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0541. Min Act: -0.0001

Data Index: 909849 (C4 (Web Text))

Max Activating Token Index: 754

Text #13

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0470. Min Act: -0.0001

Data Index: 1249436 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0540. Min Act: -0.0001

Data Index: 558113 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0489. Min Act: -0.0001

Data Index: 874984 (C4 (Web Text))

Max Activating Token Index: 508

Text #16

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0490. Min Act: -0.0001

Data Index: 229760 (C4 (Web Text))

Max Activating Token Index: 459

Text #17

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0506. Min Act: -0.0001

Data Index: 394585 (C4 (Web Text))

Max Activating Token Index: 844

Text #18

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0540. Min Act: -0.0001

Data Index: 339621 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0463. Min Act: -0.0001

Data Index: 1259820 (C4 (Web Text))

Max Activating Token Index: 125