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

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

Neuron 2903 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4761. Min Range: -1.4761

Max Act: 1.4761. Min Act: -0.0000

Data Index: 1629040 (Python Code)

Max Activating Token Index: 52

Text #1

Max Range: 1.4761. Min Range: -1.4761

Max Act: 1.3747. Min Act: -0.0000

Data Index: 1106848 (C4 (Web Text))

Max Activating Token Index: 225

Text #2

Max Range: 1.4761. Min Range: -1.4761

Max Act: 1.3483. Min Act: -0.0000

Data Index: 177315 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 1.4761. Min Range: -1.4761

Max Act: 1.3658. Min Act: -0.0000

Data Index: 224874 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 1.4761. Min Range: -1.4761

Max Act: 1.2566. Min Act: -0.0000

Data Index: 1364667 (Python Code)

Max Activating Token Index: 855

Text #5

Max Range: 1.4761. Min Range: -1.4761

Max Act: 1.2877. Min Act: -0.0000

Data Index: 1378190 (Python Code)

Max Activating Token Index: 939

Text #6

Max Range: 1.4761. Min Range: -1.4761

Max Act: 1.2568. Min Act: -0.0000

Data Index: 1044415 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 1.4761. Min Range: -1.4761

Max Act: 1.2106. Min Act: -0.0000

Data Index: 506031 (C4 (Web Text))

Max Activating Token Index: 276

Text #8

Max Range: 1.4761. Min Range: -1.4761

Max Act: 1.1113. Min Act: -0.0000

Data Index: 1535688 (Python Code)

Max Activating Token Index: 776

Text #9

Max Range: 1.4761. Min Range: -1.4761

Max Act: 1.1624. Min Act: -0.0000

Data Index: 1506735 (Python Code)

Max Activating Token Index: 669

Text #10

Max Range: 1.4761. Min Range: -1.4761

Max Act: 1.0509. Min Act: -0.0000

Data Index: 1496361 (Python Code)

Max Activating Token Index: 998

Text #11

Max Range: 1.4761. Min Range: -1.4761

Max Act: 1.0472. Min Act: -0.0000

Data Index: 1633279 (Python Code)

Max Activating Token Index: 1022

Text #12

Max Range: 1.4761. Min Range: -1.4761

Max Act: 1.1031. Min Act: -0.0000

Data Index: 1269750 (C4 (Web Text))

Max Activating Token Index: 766

Text #13

Max Range: 1.4761. Min Range: -1.4761

Max Act: 1.0795. Min Act: -0.0000

Data Index: 1619712 (Python Code)

Max Activating Token Index: 679

Text #14

Max Range: 1.4761. Min Range: -1.4761

Max Act: 1.0335. Min Act: -0.0000

Data Index: 1650185 (Python Code)

Max Activating Token Index: 197

Text #15

Max Range: 1.4761. Min Range: -1.4761

Max Act: 1.0331. Min Act: -0.0000

Data Index: 1429049 (Python Code)

Max Activating Token Index: 486

Text #16

Max Range: 1.4761. Min Range: -1.4761

Max Act: 1.0006. Min Act: -0.0000

Data Index: 1574426 (Python Code)

Max Activating Token Index: 319

Text #17

Max Range: 1.4761. Min Range: -1.4761

Max Act: 1.0310. Min Act: -0.0000

Data Index: 1436778 (Python Code)

Max Activating Token Index: 113

Text #18

Max Range: 1.4761. Min Range: -1.4761

Max Act: 0.9756. Min Act: -0.0000

Data Index: 1647638 (Python Code)

Max Activating Token Index: 949

Text #19

Max Range: 1.4761. Min Range: -1.4761

Max Act: 0.9665. Min Act: -0.0000

Data Index: 1622941 (Python Code)

Max Activating Token Index: 79