Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2297 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6511. Min Range: -1.6511

Max Act: 1.5199. Min Act: -0.0001

Data Index: 1524852 (Python Code)

Max Activating Token Index: 143

Text #1

Max Range: 1.6511. Min Range: -1.6511

Max Act: 1.6511. Min Act: -0.0001

Data Index: 1549018 (Python Code)

Max Activating Token Index: 344

Text #2

Max Range: 1.6511. Min Range: -1.6511

Max Act: 1.5075. Min Act: -0.0001

Data Index: 1472511 (Python Code)

Max Activating Token Index: 332

Text #3

Max Range: 1.6511. Min Range: -1.6511

Max Act: 1.5121. Min Act: -0.0001

Data Index: 1521902 (Python Code)

Max Activating Token Index: 565

Text #4

Max Range: 1.6511. Min Range: -1.6511

Max Act: 1.4182. Min Act: -0.0001

Data Index: 1394384 (Python Code)

Max Activating Token Index: 308

Text #5

Max Range: 1.6511. Min Range: -1.6511

Max Act: 1.4599. Min Act: -0.0001

Data Index: 1512748 (Python Code)

Max Activating Token Index: 153

Text #6

Max Range: 1.6511. Min Range: -1.6511

Max Act: 1.4019. Min Act: -0.0001

Data Index: 1630049 (Python Code)

Max Activating Token Index: 575

Text #7

Max Range: 1.6511. Min Range: -1.6511

Max Act: 1.2217. Min Act: -0.0001

Data Index: 1079917 (C4 (Web Text))

Max Activating Token Index: 247

Text #8

Max Range: 1.6511. Min Range: -1.6511

Max Act: 1.3964. Min Act: -0.0001

Data Index: 1367553 (Python Code)

Max Activating Token Index: 811

Text #9

Max Range: 1.6511. Min Range: -1.6511

Max Act: 1.3011. Min Act: -0.0001

Data Index: 1548653 (Python Code)

Max Activating Token Index: 757

Text #10

Max Range: 1.6511. Min Range: -1.6511

Max Act: 1.2834. Min Act: -0.0001

Data Index: 1567359 (Python Code)

Max Activating Token Index: 205

Text #11

Max Range: 1.6511. Min Range: -1.6511

Max Act: 1.3819. Min Act: -0.0001

Data Index: 1614529 (Python Code)

Max Activating Token Index: 687

Text #12

Max Range: 1.6511. Min Range: -1.6511

Max Act: 1.2967. Min Act: -0.0001

Data Index: 1374075 (Python Code)

Max Activating Token Index: 184

Text #13

Max Range: 1.6511. Min Range: -1.6511

Max Act: 1.3302. Min Act: -0.0001

Data Index: 431865 (C4 (Web Text))

Max Activating Token Index: 186

Text #14

Max Range: 1.6511. Min Range: -1.6511

Max Act: 1.3565. Min Act: -0.0001

Data Index: 248086 (C4 (Web Text))

Max Activating Token Index: 554

Text #15

Max Range: 1.6511. Min Range: -1.6511

Max Act: 1.2475. Min Act: -0.0001

Data Index: 362618 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 1.6511. Min Range: -1.6511

Max Act: 1.5083. Min Act: -0.0001

Data Index: 1633194 (Python Code)

Max Activating Token Index: 914

Text #17

Max Range: 1.6511. Min Range: -1.6511

Max Act: 1.2513. Min Act: -0.0001

Data Index: 1323713 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 1.6511. Min Range: -1.6511

Max Act: 1.0942. Min Act: -0.0001

Data Index: 1029806 (C4 (Web Text))

Max Activating Token Index: 536

Text #19

Max Range: 1.6511. Min Range: -1.6511

Max Act: 1.0361. Min Act: -0.0001

Data Index: 861016 (C4 (Web Text))

Max Activating Token Index: 594