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

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

Neuron 2621 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7192. Min Range: -1.7192

Max Act: 1.7192. Min Act: -0.0000

Data Index: 288785 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 1.7192. Min Range: -1.7192

Max Act: 1.6086. Min Act: -0.0000

Data Index: 273127 (C4 (Web Text))

Max Activating Token Index: 829

Text #2

Max Range: 1.7192. Min Range: -1.7192

Max Act: 1.6314. Min Act: -0.0000

Data Index: 597122 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 1.7192. Min Range: -1.7192

Max Act: 1.6483. Min Act: -0.0000

Data Index: 118287 (C4 (Web Text))

Max Activating Token Index: 405

Text #4

Max Range: 1.7192. Min Range: -1.7192

Max Act: 1.5979. Min Act: -0.0000

Data Index: 861799 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 1.7192. Min Range: -1.7192

Max Act: 1.5519. Min Act: -0.0000

Data Index: 1214127 (C4 (Web Text))

Max Activating Token Index: 412

Text #6

Max Range: 1.7192. Min Range: -1.7192

Max Act: 1.6371. Min Act: -0.0000

Data Index: 1357888 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 1.7192. Min Range: -1.7192

Max Act: 1.5839. Min Act: -0.0000

Data Index: 1036980 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 1.7192. Min Range: -1.7192

Max Act: 1.4699. Min Act: -0.0000

Data Index: 1457200 (Python Code)

Max Activating Token Index: 862

Text #9

Max Range: 1.7192. Min Range: -1.7192

Max Act: 1.4238. Min Act: -0.0001

Data Index: 1633634 (Python Code)

Max Activating Token Index: 840

Text #10

Max Range: 1.7192. Min Range: -1.7192

Max Act: 1.4872. Min Act: -0.0001

Data Index: 1066865 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 1.7192. Min Range: -1.7192

Max Act: 1.4984. Min Act: -0.0001

Data Index: 714954 (C4 (Web Text))

Max Activating Token Index: 982

Text #12

Max Range: 1.7192. Min Range: -1.7192

Max Act: 1.4888. Min Act: -0.0001

Data Index: 1030133 (C4 (Web Text))

Max Activating Token Index: 570

Text #13

Max Range: 1.7192. Min Range: -1.7192

Max Act: 1.4802. Min Act: -0.0000

Data Index: 667156 (C4 (Web Text))

Max Activating Token Index: 221

Text #14

Max Range: 1.7192. Min Range: -1.7192

Max Act: 1.4797. Min Act: -0.0000

Data Index: 212459 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 1.7192. Min Range: -1.7192

Max Act: 1.5151. Min Act: -0.0000

Data Index: 966585 (C4 (Web Text))

Max Activating Token Index: 341

Text #16

Max Range: 1.7192. Min Range: -1.7192

Max Act: 1.6007. Min Act: -0.0001

Data Index: 1539327 (Python Code)

Max Activating Token Index: 615

Text #17

Max Range: 1.7192. Min Range: -1.7192

Max Act: 1.4503. Min Act: -0.0000

Data Index: 1049203 (C4 (Web Text))

Max Activating Token Index: 245

Text #18

Max Range: 1.7192. Min Range: -1.7192

Max Act: 1.4310. Min Act: -0.0000

Data Index: 374308 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 1.7192. Min Range: -1.7192

Max Act: 1.4658. Min Act: -0.0000

Data Index: 208981 (C4 (Web Text))

Max Activating Token Index: 986