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

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

Neuron 3766 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9658. Min Range: -0.9658

Max Act: 0.9658. Min Act: -0.0001

Data Index: 298264 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 0.9658. Min Range: -0.9658

Max Act: 0.8848. Min Act: -0.0001

Data Index: 416567 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 0.9658. Min Range: -0.9658

Max Act: 0.8995. Min Act: -0.0001

Data Index: 761302 (C4 (Web Text))

Max Activating Token Index: 532

Text #3

Max Range: 0.9658. Min Range: -0.9658

Max Act: 0.7588. Min Act: -0.0001

Data Index: 730285 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 0.9658. Min Range: -0.9658

Max Act: 0.8126. Min Act: -0.0001

Data Index: 442299 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 0.9658. Min Range: -0.9658

Max Act: 0.7418. Min Act: -0.0001

Data Index: 579045 (C4 (Web Text))

Max Activating Token Index: 808

Text #6

Max Range: 0.9658. Min Range: -0.9658

Max Act: 0.6606. Min Act: -0.0001

Data Index: 253598 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 0.9658. Min Range: -0.9658

Max Act: 0.7017. Min Act: -0.0001

Data Index: 1277697 (C4 (Web Text))

Max Activating Token Index: 996

Text #8

Max Range: 0.9658. Min Range: -0.9658

Max Act: 0.7607. Min Act: -0.0001

Data Index: 1282010 (C4 (Web Text))

Max Activating Token Index: 843

Text #9

Max Range: 0.9658. Min Range: -0.9658

Max Act: 0.7059. Min Act: -0.0001

Data Index: 447876 (C4 (Web Text))

Max Activating Token Index: 152

Text #10

Max Range: 0.9658. Min Range: -0.9658

Max Act: 0.6922. Min Act: -0.0001

Data Index: 929156 (C4 (Web Text))

Max Activating Token Index: 476

Text #11

Max Range: 0.9658. Min Range: -0.9658

Max Act: 0.6067. Min Act: -0.0001

Data Index: 183955 (C4 (Web Text))

Max Activating Token Index: 960

Text #12

Max Range: 0.9658. Min Range: -0.9658

Max Act: 0.5620. Min Act: -0.0001

Data Index: 460297 (C4 (Web Text))

Max Activating Token Index: 930

Text #13

Max Range: 0.9658. Min Range: -0.9658

Max Act: 0.6747. Min Act: -0.0001

Data Index: 58284 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 0.9658. Min Range: -0.9658

Max Act: 0.6509. Min Act: -0.0001

Data Index: 112890 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 0.9658. Min Range: -0.9658

Max Act: 0.6161. Min Act: -0.0000

Data Index: 319025 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 0.9658. Min Range: -0.9658

Max Act: 0.6575. Min Act: -0.0001

Data Index: 30574 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 0.9658. Min Range: -0.9658

Max Act: 0.6759. Min Act: -0.0001

Data Index: 154004 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 0.9658. Min Range: -0.9658

Max Act: 0.5725. Min Act: -0.0001

Data Index: 665747 (C4 (Web Text))

Max Activating Token Index: 306

Text #19

Max Range: 0.9658. Min Range: -0.9658

Max Act: 0.6727. Min Act: -0.0000

Data Index: 941266 (C4 (Web Text))

Max Activating Token Index: 422