Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6125 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.6635. Min Act: -0.0000

Data Index: 1362682 (Python Code)

Max Activating Token Index: 675

Text #1

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.6117. Min Act: -0.0000

Data Index: 1540948 (Python Code)

Max Activating Token Index: 715

Text #2

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.4707. Min Act: -0.0000

Data Index: 1618888 (Python Code)

Max Activating Token Index: 176

Text #3

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.4610. Min Act: -0.0000

Data Index: 965095 (C4 (Web Text))

Max Activating Token Index: 398

Text #4

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.3947. Min Act: -0.0000

Data Index: 1452407 (Python Code)

Max Activating Token Index: 587

Text #5

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.4111. Min Act: -0.0000

Data Index: 1361836 (Python Code)

Max Activating Token Index: 213

Text #6

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.4000. Min Act: -0.0000

Data Index: 1561994 (Python Code)

Max Activating Token Index: 380

Text #7

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.3743. Min Act: -0.0000

Data Index: 1457412 (Python Code)

Max Activating Token Index: 368

Text #8

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.3642. Min Act: -0.0000

Data Index: 1424548 (Python Code)

Max Activating Token Index: 397

Text #9

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.4022. Min Act: -0.0000

Data Index: 1602173 (Python Code)

Max Activating Token Index: 907

Text #10

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.3988. Min Act: -0.0000

Data Index: 1481786 (Python Code)

Max Activating Token Index: 551

Text #11

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.3785. Min Act: -0.0000

Data Index: 736103 (C4 (Web Text))

Max Activating Token Index: 961

Text #12

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.3583. Min Act: -0.0000

Data Index: 1616823 (Python Code)

Max Activating Token Index: 88

Text #13

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.3235. Min Act: -0.0000

Data Index: 529064 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.3321. Min Act: -0.0000

Data Index: 445149 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.3360. Min Act: -0.0000

Data Index: 1164537 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.3218. Min Act: -0.0000

Data Index: 1398796 (Python Code)

Max Activating Token Index: 161

Text #17

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.2965. Min Act: -0.0000

Data Index: 1370588 (Python Code)

Max Activating Token Index: 926

Text #18

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.2960. Min Act: -0.0000

Data Index: 1617172 (Python Code)

Max Activating Token Index: 530

Text #19

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.3007. Min Act: -0.0000

Data Index: 251648 (C4 (Web Text))

Max Activating Token Index: 180