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

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

Neuron 3638 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: 0.8589. Min Range: -0.8589

Max Act: 0.8589. Min Act: 0.0000

Data Index: 820294 (C4 (Web Text))

Max Activating Token Index: 491

Text #1

Max Range: 0.8589. Min Range: -0.8589

Max Act: 0.7584. Min Act: -0.0000

Data Index: 398795 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 0.8589. Min Range: -0.8589

Max Act: 0.6759. Min Act: -0.0000

Data Index: 431465 (C4 (Web Text))

Max Activating Token Index: 946

Text #3

Max Range: 0.8589. Min Range: -0.8589

Max Act: 0.6377. Min Act: -0.0000

Data Index: 916578 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 0.8589. Min Range: -0.8589

Max Act: 0.6925. Min Act: -0.0000

Data Index: 435676 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 0.8589. Min Range: -0.8589

Max Act: 0.6455. Min Act: -0.0000

Data Index: 1168613 (C4 (Web Text))

Max Activating Token Index: 634

Text #6

Max Range: 0.8589. Min Range: -0.8589

Max Act: 0.6822. Min Act: -0.0000

Data Index: 790500 (C4 (Web Text))

Max Activating Token Index: 691

Text #7

Max Range: 0.8589. Min Range: -0.8589

Max Act: 0.6545. Min Act: -0.0000

Data Index: 983778 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 0.8589. Min Range: -0.8589

Max Act: 0.6383. Min Act: -0.0000

Data Index: 1085634 (C4 (Web Text))

Max Activating Token Index: 861

Text #9

Max Range: 0.8589. Min Range: -0.8589

Max Act: 0.6093. Min Act: -0.0000

Data Index: 835908 (C4 (Web Text))

Max Activating Token Index: 673

Text #10

Max Range: 0.8589. Min Range: -0.8589

Max Act: 0.6052. Min Act: -0.0000

Data Index: 277894 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 0.8589. Min Range: -0.8589

Max Act: 0.6209. Min Act: -0.0000

Data Index: 818273 (C4 (Web Text))

Max Activating Token Index: 943

Text #12

Max Range: 0.8589. Min Range: -0.8589

Max Act: 0.6132. Min Act: 0.0000

Data Index: 856561 (C4 (Web Text))

Max Activating Token Index: 227

Text #13

Max Range: 0.8589. Min Range: -0.8589

Max Act: 0.6073. Min Act: -0.0000

Data Index: 588420 (C4 (Web Text))

Max Activating Token Index: 696

Text #14

Max Range: 0.8589. Min Range: -0.8589

Max Act: 0.6113. Min Act: 0.0000

Data Index: 17053 (C4 (Web Text))

Max Activating Token Index: 41

Text #15

Max Range: 0.8589. Min Range: -0.8589

Max Act: 0.5999. Min Act: 0.0001

Data Index: 380327 (C4 (Web Text))

Max Activating Token Index: 742

Text #16

Max Range: 0.8589. Min Range: -0.8589

Max Act: 0.6017. Min Act: 0.0000

Data Index: 107640 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 0.8589. Min Range: -0.8589

Max Act: 0.6624. Min Act: 0.0000

Data Index: 784773 (C4 (Web Text))

Max Activating Token Index: 775

Text #18

Max Range: 0.8589. Min Range: -0.8589

Max Act: 0.6008. Min Act: -0.0000

Data Index: 219502 (C4 (Web Text))

Max Activating Token Index: 497

Text #19

Max Range: 0.8589. Min Range: -0.8589

Max Act: 0.5754. Min Act: -0.0000

Data Index: 758860 (C4 (Web Text))

Max Activating Token Index: 625