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

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

Neuron 4359 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.3014. Min Act: -0.0000

Data Index: 1118484 (C4 (Web Text))

Max Activating Token Index: 516

Text #1

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.2883. Min Act: -0.0000

Data Index: 773058 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.2790. Min Act: -0.0000

Data Index: 411234 (C4 (Web Text))

Max Activating Token Index: 342

Text #3

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.2727. Min Act: -0.0000

Data Index: 530657 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.2696. Min Act: -0.0000

Data Index: 292727 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.2978. Min Act: -0.0000

Data Index: 102499 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.2785. Min Act: -0.0000

Data Index: 1190107 (C4 (Web Text))

Max Activating Token Index: 313

Text #7

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.2587. Min Act: -0.0000

Data Index: 1093937 (C4 (Web Text))

Max Activating Token Index: 741

Text #8

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.2590. Min Act: -0.0000

Data Index: 438111 (C4 (Web Text))

Max Activating Token Index: 964

Text #9

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.2544. Min Act: -0.0000

Data Index: 664221 (C4 (Web Text))

Max Activating Token Index: 227

Text #10

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.2533. Min Act: -0.0000

Data Index: 698187 (C4 (Web Text))

Max Activating Token Index: 226

Text #11

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.2519. Min Act: -0.0000

Data Index: 1326869 (C4 (Web Text))

Max Activating Token Index: 561

Text #12

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.2480. Min Act: -0.0000

Data Index: 749814 (C4 (Web Text))

Max Activating Token Index: 478

Text #13

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.2463. Min Act: -0.0000

Data Index: 871168 (C4 (Web Text))

Max Activating Token Index: 973

Text #14

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.2625. Min Act: -0.0000

Data Index: 161984 (C4 (Web Text))

Max Activating Token Index: 887

Text #15

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.2548. Min Act: -0.0000

Data Index: 284180 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.2492. Min Act: -0.0000

Data Index: 494205 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.2343. Min Act: -0.0000

Data Index: 1118857 (C4 (Web Text))

Max Activating Token Index: 146

Text #18

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.2601. Min Act: -0.0000

Data Index: 165270 (C4 (Web Text))

Max Activating Token Index: 153

Text #19

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.2404. Min Act: -0.0000

Data Index: 182270 (C4 (Web Text))

Max Activating Token Index: 353