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

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

Neuron 2025 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.9908. Min Act: -0.0000

Data Index: 416720 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.9861. Min Act: -0.0000

Data Index: 1077854 (C4 (Web Text))

Max Activating Token Index: 199

Text #2

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.8304. Min Act: -0.0000

Data Index: 1200954 (C4 (Web Text))

Max Activating Token Index: 660

Text #3

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.8701. Min Act: -0.0000

Data Index: 218262 (C4 (Web Text))

Max Activating Token Index: 185

Text #4

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.8615. Min Act: -0.0000

Data Index: 24155 (C4 (Web Text))

Max Activating Token Index: 838

Text #5

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.7658. Min Act: -0.0000

Data Index: 215865 (C4 (Web Text))

Max Activating Token Index: 225

Text #6

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.8052. Min Act: -0.0000

Data Index: 109500 (C4 (Web Text))

Max Activating Token Index: 1003

Text #7

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.7539. Min Act: -0.0000

Data Index: 156937 (C4 (Web Text))

Max Activating Token Index: 850

Text #8

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.7631. Min Act: -0.0000

Data Index: 317596 (C4 (Web Text))

Max Activating Token Index: 501

Text #9

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.7864. Min Act: -0.0000

Data Index: 652374 (C4 (Web Text))

Max Activating Token Index: 256

Text #10

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.7457. Min Act: -0.0000

Data Index: 855619 (C4 (Web Text))

Max Activating Token Index: 319

Text #11

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.7051. Min Act: -0.0000

Data Index: 1200492 (C4 (Web Text))

Max Activating Token Index: 143

Text #12

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.7249. Min Act: -0.0000

Data Index: 1108879 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.7218. Min Act: -0.0000

Data Index: 275875 (C4 (Web Text))

Max Activating Token Index: 895

Text #14

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.7438. Min Act: -0.0000

Data Index: 1320096 (C4 (Web Text))

Max Activating Token Index: 478

Text #15

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.7482. Min Act: -0.0000

Data Index: 552905 (C4 (Web Text))

Max Activating Token Index: 985

Text #16

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.7222. Min Act: -0.0000

Data Index: 1305938 (C4 (Web Text))

Max Activating Token Index: 136

Text #17

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.7208. Min Act: -0.0000

Data Index: 504861 (C4 (Web Text))

Max Activating Token Index: 766

Text #18

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.6729. Min Act: -0.0000

Data Index: 228816 (C4 (Web Text))

Max Activating Token Index: 293

Text #19

Max Range: 0.9908. Min Range: -0.9908

Max Act: 0.6444. Min Act: -0.0000

Data Index: 157829 (C4 (Web Text))

Max Activating Token Index: 494