Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 803 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.9289. Min Act: -0.0002

Data Index: 622803 (C4 (Web Text))

Max Activating Token Index: 589

Text #1

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.8320. Min Act: -0.0002

Data Index: 594281 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.7463. Min Act: -0.0002

Data Index: 1055875 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.7480. Min Act: -0.0002

Data Index: 135037 (C4 (Web Text))

Max Activating Token Index: 207

Text #4

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.7199. Min Act: -0.0002

Data Index: 732133 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.7154. Min Act: -0.0002

Data Index: 832766 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.6842. Min Act: -0.0002

Data Index: 310761 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.6955. Min Act: -0.0002

Data Index: 20448 (C4 (Web Text))

Max Activating Token Index: 458

Text #8

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.6878. Min Act: -0.0002

Data Index: 331952 (C4 (Web Text))

Max Activating Token Index: 188

Text #9

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.6526. Min Act: -0.0002

Data Index: 685213 (C4 (Web Text))

Max Activating Token Index: 709

Text #10

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.6731. Min Act: -0.0002

Data Index: 1190960 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.6702. Min Act: -0.0002

Data Index: 500125 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.6604. Min Act: -0.0002

Data Index: 1272607 (C4 (Web Text))

Max Activating Token Index: 85

Text #13

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.6330. Min Act: -0.0002

Data Index: 525591 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.6470. Min Act: -0.0002

Data Index: 1089679 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.6316. Min Act: -0.0002

Data Index: 101669 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.6464. Min Act: -0.0002

Data Index: 1015158 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.6591. Min Act: -0.0002

Data Index: 1286917 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.6190. Min Act: -0.0002

Data Index: 83410 (C4 (Web Text))

Max Activating Token Index: 559

Text #19

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.6575. Min Act: -0.0002

Data Index: 1050085 (C4 (Web Text))

Max Activating Token Index: 62