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

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

Neuron 1975 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6588. Min Range: -0.6588

Max Act: 0.5836. Min Act: -0.0000

Data Index: 362743 (C4 (Web Text))

Max Activating Token Index: 471

Text #1

Max Range: 0.6588. Min Range: -0.6588

Max Act: 0.6588. Min Act: -0.0000

Data Index: 763182 (C4 (Web Text))

Max Activating Token Index: 355

Text #2

Max Range: 0.6588. Min Range: -0.6588

Max Act: 0.6184. Min Act: -0.0000

Data Index: 1475558 (Python Code)

Max Activating Token Index: 980

Text #3

Max Range: 0.6588. Min Range: -0.6588

Max Act: 0.5820. Min Act: -0.0000

Data Index: 1634359 (Python Code)

Max Activating Token Index: 740

Text #4

Max Range: 0.6588. Min Range: -0.6588

Max Act: 0.5680. Min Act: -0.0000

Data Index: 1396056 (Python Code)

Max Activating Token Index: 743

Text #5

Max Range: 0.6588. Min Range: -0.6588

Max Act: 0.5570. Min Act: -0.0000

Data Index: 646962 (C4 (Web Text))

Max Activating Token Index: 365

Text #6

Max Range: 0.6588. Min Range: -0.6588

Max Act: 0.5839. Min Act: -0.0000

Data Index: 748884 (C4 (Web Text))

Max Activating Token Index: 462

Text #7

Max Range: 0.6588. Min Range: -0.6588

Max Act: 0.5838. Min Act: -0.0000

Data Index: 1611788 (Python Code)

Max Activating Token Index: 869

Text #8

Max Range: 0.6588. Min Range: -0.6588

Max Act: 0.5798. Min Act: -0.0000

Data Index: 986573 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 0.6588. Min Range: -0.6588

Max Act: 0.6347. Min Act: -0.0000

Data Index: 1451461 (Python Code)

Max Activating Token Index: 225

Text #10

Max Range: 0.6588. Min Range: -0.6588

Max Act: 0.5384. Min Act: -0.0000

Data Index: 632882 (C4 (Web Text))

Max Activating Token Index: 802

Text #11

Max Range: 0.6588. Min Range: -0.6588

Max Act: 0.5384. Min Act: -0.0000

Data Index: 1510127 (Python Code)

Max Activating Token Index: 642

Text #12

Max Range: 0.6588. Min Range: -0.6588

Max Act: 0.5555. Min Act: -0.0000

Data Index: 562987 (C4 (Web Text))

Max Activating Token Index: 777

Text #13

Max Range: 0.6588. Min Range: -0.6588

Max Act: 0.5302. Min Act: -0.0000

Data Index: 901557 (C4 (Web Text))

Max Activating Token Index: 474

Text #14

Max Range: 0.6588. Min Range: -0.6588

Max Act: 0.4671. Min Act: -0.0000

Data Index: 404315 (C4 (Web Text))

Max Activating Token Index: 547

Text #15

Max Range: 0.6588. Min Range: -0.6588

Max Act: 0.5391. Min Act: -0.0000

Data Index: 245398 (C4 (Web Text))

Max Activating Token Index: 385

Text #16

Max Range: 0.6588. Min Range: -0.6588

Max Act: 0.4941. Min Act: -0.0000

Data Index: 746711 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 0.6588. Min Range: -0.6588

Max Act: 0.5168. Min Act: -0.0000

Data Index: 296912 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 0.6588. Min Range: -0.6588

Max Act: 0.4819. Min Act: -0.0000

Data Index: 130039 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 0.6588. Min Range: -0.6588

Max Act: 0.5268. Min Act: -0.0000

Data Index: 248098 (C4 (Web Text))

Max Activating Token Index: 105