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

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

Neuron 2708 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.3992. Min Act: -0.0001

Data Index: 1644502 (Python Code)

Max Activating Token Index: 19

Text #1

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.3781. Min Act: -0.0001

Data Index: 1387493 (Python Code)

Max Activating Token Index: 796

Text #2

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.3792. Min Act: -0.0001

Data Index: 1513728 (Python Code)

Max Activating Token Index: 26

Text #3

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.3664. Min Act: -0.0001

Data Index: 1444623 (Python Code)

Max Activating Token Index: 769

Text #4

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.3859. Min Act: -0.0001

Data Index: 1632604 (Python Code)

Max Activating Token Index: 375

Text #5

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.4052. Min Act: -0.0001

Data Index: 1645990 (Python Code)

Max Activating Token Index: 295

Text #6

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.3711. Min Act: -0.0001

Data Index: 1444100 (Python Code)

Max Activating Token Index: 39

Text #7

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.3565. Min Act: -0.0001

Data Index: 1625220 (Python Code)

Max Activating Token Index: 119

Text #8

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.3672. Min Act: -0.0001

Data Index: 1584714 (Python Code)

Max Activating Token Index: 33

Text #9

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.3313. Min Act: -0.0001

Data Index: 1388248 (Python Code)

Max Activating Token Index: 530

Text #10

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.3665. Min Act: -0.0001

Data Index: 1472819 (Python Code)

Max Activating Token Index: 21

Text #11

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.3652. Min Act: -0.0001

Data Index: 1567625 (Python Code)

Max Activating Token Index: 950

Text #12

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.3647. Min Act: -0.0001

Data Index: 1433648 (Python Code)

Max Activating Token Index: 32

Text #13

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.3676. Min Act: -0.0001

Data Index: 1470063 (Python Code)

Max Activating Token Index: 94

Text #14

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.3452. Min Act: -0.0001

Data Index: 1447212 (Python Code)

Max Activating Token Index: 38

Text #15

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.3554. Min Act: -0.0001

Data Index: 1553978 (Python Code)

Max Activating Token Index: 57

Text #16

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.3393. Min Act: -0.0001

Data Index: 1591411 (Python Code)

Max Activating Token Index: 968

Text #17

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.3325. Min Act: -0.0001

Data Index: 1560948 (Python Code)

Max Activating Token Index: 38

Text #18

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.3429. Min Act: -0.0001

Data Index: 1505146 (Python Code)

Max Activating Token Index: 27

Text #19

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.3423. Min Act: -0.0001

Data Index: 1650422 (Python Code)

Max Activating Token Index: 258