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

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

Neuron 2265 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2990. Min Range: -1.2990

Max Act: 1.2990. Min Act: -0.0000

Data Index: 1205571 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 1.2990. Min Range: -1.2990

Max Act: 1.1581. Min Act: -0.0000

Data Index: 380111 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 1.2990. Min Range: -1.2990

Max Act: 1.1236. Min Act: -0.0000

Data Index: 811429 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 1.2990. Min Range: -1.2990

Max Act: 1.0352. Min Act: -0.0000

Data Index: 967386 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 1.2990. Min Range: -1.2990

Max Act: 0.9497. Min Act: -0.0000

Data Index: 1243213 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 1.2990. Min Range: -1.2990

Max Act: 0.8431. Min Act: -0.0000

Data Index: 224967 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 1.2990. Min Range: -1.2990

Max Act: 0.7741. Min Act: -0.0000

Data Index: 1002226 (C4 (Web Text))

Max Activating Token Index: 717

Text #7

Max Range: 1.2990. Min Range: -1.2990

Max Act: 0.8667. Min Act: -0.0000

Data Index: 1000060 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 1.2990. Min Range: -1.2990

Max Act: 0.8607. Min Act: -0.0000

Data Index: 20502 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 1.2990. Min Range: -1.2990

Max Act: 0.8664. Min Act: -0.0000

Data Index: 62793 (C4 (Web Text))

Max Activating Token Index: 873

Text #10

Max Range: 1.2990. Min Range: -1.2990

Max Act: 0.8610. Min Act: -0.0000

Data Index: 615120 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 1.2990. Min Range: -1.2990

Max Act: 0.7835. Min Act: -0.0000

Data Index: 1003625 (C4 (Web Text))

Max Activating Token Index: 801

Text #12

Max Range: 1.2990. Min Range: -1.2990

Max Act: 0.8256. Min Act: -0.0000

Data Index: 883734 (C4 (Web Text))

Max Activating Token Index: 869

Text #13

Max Range: 1.2990. Min Range: -1.2990

Max Act: 0.8150. Min Act: -0.0000

Data Index: 2409 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 1.2990. Min Range: -1.2990

Max Act: 0.7546. Min Act: -0.0000

Data Index: 144552 (C4 (Web Text))

Max Activating Token Index: 118

Text #15

Max Range: 1.2990. Min Range: -1.2990

Max Act: 0.8162. Min Act: -0.0000

Data Index: 1246261 (C4 (Web Text))

Max Activating Token Index: 326

Text #16

Max Range: 1.2990. Min Range: -1.2990

Max Act: 0.7014. Min Act: -0.0000

Data Index: 454623 (C4 (Web Text))

Max Activating Token Index: 698

Text #17

Max Range: 1.2990. Min Range: -1.2990

Max Act: 0.6472. Min Act: -0.0000

Data Index: 529643 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 1.2990. Min Range: -1.2990

Max Act: 0.8480. Min Act: -0.0000

Data Index: 1358967 (C4 (Web Text))

Max Activating Token Index: 624

Text #19

Max Range: 1.2990. Min Range: -1.2990

Max Act: 0.7267. Min Act: -0.0000

Data Index: 601569 (C4 (Web Text))

Max Activating Token Index: 28