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

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

Neuron 2207 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: 1.1379. Min Range: -1.1379

Max Act: 1.1379. Min Act: -0.0000

Data Index: 139775 (C4 (Web Text))

Max Activating Token Index: 462

Text #1

Max Range: 1.1379. Min Range: -1.1379

Max Act: 1.0379. Min Act: -0.0000

Data Index: 1139425 (C4 (Web Text))

Max Activating Token Index: 744

Text #2

Max Range: 1.1379. Min Range: -1.1379

Max Act: 0.9714. Min Act: -0.0000

Data Index: 174210 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 1.1379. Min Range: -1.1379

Max Act: 0.9982. Min Act: -0.0000

Data Index: 504204 (C4 (Web Text))

Max Activating Token Index: 452

Text #4

Max Range: 1.1379. Min Range: -1.1379

Max Act: 0.9558. Min Act: -0.0000

Data Index: 426172 (C4 (Web Text))

Max Activating Token Index: 655

Text #5

Max Range: 1.1379. Min Range: -1.1379

Max Act: 0.9425. Min Act: -0.0000

Data Index: 908952 (C4 (Web Text))

Max Activating Token Index: 271

Text #6

Max Range: 1.1379. Min Range: -1.1379

Max Act: 0.9442. Min Act: -0.0000

Data Index: 846449 (C4 (Web Text))

Max Activating Token Index: 801

Text #7

Max Range: 1.1379. Min Range: -1.1379

Max Act: 0.9460. Min Act: -0.0000

Data Index: 393389 (C4 (Web Text))

Max Activating Token Index: 908

Text #8

Max Range: 1.1379. Min Range: -1.1379

Max Act: 0.9550. Min Act: -0.0000

Data Index: 748448 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 1.1379. Min Range: -1.1379

Max Act: 0.8990. Min Act: -0.0000

Data Index: 1123505 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 1.1379. Min Range: -1.1379

Max Act: 0.9507. Min Act: -0.0000

Data Index: 1299035 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 1.1379. Min Range: -1.1379

Max Act: 0.9327. Min Act: -0.0000

Data Index: 474054 (C4 (Web Text))

Max Activating Token Index: 849

Text #12

Max Range: 1.1379. Min Range: -1.1379

Max Act: 0.9320. Min Act: -0.0000

Data Index: 377766 (C4 (Web Text))

Max Activating Token Index: 45

Text #13

Max Range: 1.1379. Min Range: -1.1379

Max Act: 0.8664. Min Act: -0.0000

Data Index: 1381331 (Python Code)

Max Activating Token Index: 324

Text #14

Max Range: 1.1379. Min Range: -1.1379

Max Act: 0.8943. Min Act: -0.0000

Data Index: 1301556 (C4 (Web Text))

Max Activating Token Index: 450

Text #15

Max Range: 1.1379. Min Range: -1.1379

Max Act: 0.8937. Min Act: -0.0000

Data Index: 756127 (C4 (Web Text))

Max Activating Token Index: 489

Text #16

Max Range: 1.1379. Min Range: -1.1379

Max Act: 0.8753. Min Act: -0.0000

Data Index: 614763 (C4 (Web Text))

Max Activating Token Index: 281

Text #17

Max Range: 1.1379. Min Range: -1.1379

Max Act: 0.8470. Min Act: -0.0000

Data Index: 198739 (C4 (Web Text))

Max Activating Token Index: 947

Text #18

Max Range: 1.1379. Min Range: -1.1379

Max Act: 0.9227. Min Act: -0.0000

Data Index: 1569673 (Python Code)

Max Activating Token Index: 872

Text #19

Max Range: 1.1379. Min Range: -1.1379

Max Act: 0.9221. Min Act: -0.0000

Data Index: 1544755 (Python Code)

Max Activating Token Index: 941