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

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

Neuron 3816 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1436. Min Act: -0.0001

Data Index: 241653 (C4 (Web Text))

Max Activating Token Index: 429

Text #1

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1335. Min Act: -0.0001

Data Index: 829943 (C4 (Web Text))

Max Activating Token Index: 692

Text #2

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1143. Min Act: -0.0001

Data Index: 1303204 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.0873. Min Act: -0.0001

Data Index: 950779 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1044. Min Act: -0.0001

Data Index: 962309 (C4 (Web Text))

Max Activating Token Index: 745

Text #5

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1111. Min Act: -0.0001

Data Index: 1267617 (C4 (Web Text))

Max Activating Token Index: 757

Text #6

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1072. Min Act: -0.0000

Data Index: 875064 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.0969. Min Act: -0.0000

Data Index: 333811 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.0868. Min Act: -0.0001

Data Index: 100931 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.0851. Min Act: -0.0001

Data Index: 49253 (C4 (Web Text))

Max Activating Token Index: 459

Text #10

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.0803. Min Act: -0.0001

Data Index: 1010629 (C4 (Web Text))

Max Activating Token Index: 188

Text #11

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.0825. Min Act: -0.0001

Data Index: 595576 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.0822. Min Act: -0.0000

Data Index: 101776 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.0935. Min Act: -0.0001

Data Index: 687495 (C4 (Web Text))

Max Activating Token Index: 642

Text #14

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.0849. Min Act: -0.0001

Data Index: 693094 (C4 (Web Text))

Max Activating Token Index: 230

Text #15

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.0782. Min Act: -0.0001

Data Index: 1142623 (C4 (Web Text))

Max Activating Token Index: 978

Text #16

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.0802. Min Act: -0.0001

Data Index: 257132 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.0688. Min Act: -0.0001

Data Index: 1112208 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.0785. Min Act: -0.0001

Data Index: 849341 (C4 (Web Text))

Max Activating Token Index: 511

Text #19

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.0782. Min Act: -0.0001

Data Index: 94768 (C4 (Web Text))

Max Activating Token Index: 654