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

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

Neuron 739 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: 0.4730. Min Range: -0.4730

Max Act: 0.4730. Min Act: -0.0000

Data Index: 1370937 (Python Code)

Max Activating Token Index: 356

Text #1

Max Range: 0.4730. Min Range: -0.4730

Max Act: 0.4622. Min Act: -0.0000

Data Index: 1577230 (Python Code)

Max Activating Token Index: 545

Text #2

Max Range: 0.4730. Min Range: -0.4730

Max Act: 0.4497. Min Act: -0.0000

Data Index: 1488026 (Python Code)

Max Activating Token Index: 563

Text #3

Max Range: 0.4730. Min Range: -0.4730

Max Act: 0.4160. Min Act: -0.0000

Data Index: 1643787 (Python Code)

Max Activating Token Index: 569

Text #4

Max Range: 0.4730. Min Range: -0.4730

Max Act: 0.3927. Min Act: -0.0000

Data Index: 1504198 (Python Code)

Max Activating Token Index: 595

Text #5

Max Range: 0.4730. Min Range: -0.4730

Max Act: 0.3997. Min Act: -0.0000

Data Index: 1637894 (Python Code)

Max Activating Token Index: 341

Text #6

Max Range: 0.4730. Min Range: -0.4730

Max Act: 0.4133. Min Act: -0.0000

Data Index: 1411272 (Python Code)

Max Activating Token Index: 629

Text #7

Max Range: 0.4730. Min Range: -0.4730

Max Act: 0.4095. Min Act: -0.0000

Data Index: 1411606 (Python Code)

Max Activating Token Index: 937

Text #8

Max Range: 0.4730. Min Range: -0.4730

Max Act: 0.3728. Min Act: -0.0000

Data Index: 1415729 (Python Code)

Max Activating Token Index: 839

Text #9

Max Range: 0.4730. Min Range: -0.4730

Max Act: 0.3638. Min Act: 0.0000

Data Index: 1461952 (Python Code)

Max Activating Token Index: 53

Text #10

Max Range: 0.4730. Min Range: -0.4730

Max Act: 0.3672. Min Act: -0.0000

Data Index: 1469573 (Python Code)

Max Activating Token Index: 593

Text #11

Max Range: 0.4730. Min Range: -0.4730

Max Act: 0.3826. Min Act: -0.0000

Data Index: 92174 (C4 (Web Text))

Max Activating Token Index: 923

Text #12

Max Range: 0.4730. Min Range: -0.4730

Max Act: 0.3613. Min Act: -0.0000

Data Index: 1198989 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 0.4730. Min Range: -0.4730

Max Act: 0.3425. Min Act: -0.0000

Data Index: 1418702 (Python Code)

Max Activating Token Index: 630

Text #14

Max Range: 0.4730. Min Range: -0.4730

Max Act: 0.3348. Min Act: -0.0000

Data Index: 1646837 (Python Code)

Max Activating Token Index: 472

Text #15

Max Range: 0.4730. Min Range: -0.4730

Max Act: 0.3210. Min Act: -0.0000

Data Index: 1619884 (Python Code)

Max Activating Token Index: 785

Text #16

Max Range: 0.4730. Min Range: -0.4730

Max Act: 0.3315. Min Act: -0.0000

Data Index: 1647561 (Python Code)

Max Activating Token Index: 483

Text #17

Max Range: 0.4730. Min Range: -0.4730

Max Act: 0.3486. Min Act: -0.0000

Data Index: 1505709 (Python Code)

Max Activating Token Index: 721

Text #18

Max Range: 0.4730. Min Range: -0.4730

Max Act: 0.3263. Min Act: -0.0000

Data Index: 1597647 (Python Code)

Max Activating Token Index: 392

Text #19

Max Range: 0.4730. Min Range: -0.4730

Max Act: 0.3211. Min Act: -0.0000

Data Index: 1369800 (Python Code)

Max Activating Token Index: 651