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

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

Neuron 3471 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5839. Min Range: -0.5839

Max Act: 0.5839. Min Act: -0.0000

Data Index: 1409693 (Python Code)

Max Activating Token Index: 984

Text #1

Max Range: 0.5839. Min Range: -0.5839

Max Act: 0.3778. Min Act: -0.0000

Data Index: 1460594 (Python Code)

Max Activating Token Index: 1012

Text #2

Max Range: 0.5839. Min Range: -0.5839

Max Act: 0.4284. Min Act: -0.0000

Data Index: 1359416 (C4 (Web Text))

Max Activating Token Index: 258

Text #3

Max Range: 0.5839. Min Range: -0.5839

Max Act: 0.3851. Min Act: -0.0000

Data Index: 640251 (C4 (Web Text))

Max Activating Token Index: 653

Text #4

Max Range: 0.5839. Min Range: -0.5839

Max Act: 0.4048. Min Act: -0.0000

Data Index: 1376789 (Python Code)

Max Activating Token Index: 940

Text #5

Max Range: 0.5839. Min Range: -0.5839

Max Act: 0.3971. Min Act: -0.0000

Data Index: 1598527 (Python Code)

Max Activating Token Index: 621

Text #6

Max Range: 0.5839. Min Range: -0.5839

Max Act: 0.3881. Min Act: -0.0000

Data Index: 1542480 (Python Code)

Max Activating Token Index: 344

Text #7

Max Range: 0.5839. Min Range: -0.5839

Max Act: 0.3840. Min Act: -0.0000

Data Index: 1153120 (C4 (Web Text))

Max Activating Token Index: 479

Text #8

Max Range: 0.5839. Min Range: -0.5839

Max Act: 0.3471. Min Act: -0.0000

Data Index: 1604327 (Python Code)

Max Activating Token Index: 543

Text #9

Max Range: 0.5839. Min Range: -0.5839

Max Act: 0.3091. Min Act: -0.0000

Data Index: 693076 (C4 (Web Text))

Max Activating Token Index: 545

Text #10

Max Range: 0.5839. Min Range: -0.5839

Max Act: 0.3189. Min Act: -0.0000

Data Index: 435144 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 0.5839. Min Range: -0.5839

Max Act: 0.3480. Min Act: -0.0000

Data Index: 596948 (C4 (Web Text))

Max Activating Token Index: 189

Text #12

Max Range: 0.5839. Min Range: -0.5839

Max Act: 0.3110. Min Act: -0.0000

Data Index: 1610326 (Python Code)

Max Activating Token Index: 908

Text #13

Max Range: 0.5839. Min Range: -0.5839

Max Act: 0.3330. Min Act: -0.0000

Data Index: 1527649 (Python Code)

Max Activating Token Index: 471

Text #14

Max Range: 0.5839. Min Range: -0.5839

Max Act: 0.3193. Min Act: -0.0000

Data Index: 413905 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 0.5839. Min Range: -0.5839

Max Act: 0.3074. Min Act: -0.0000

Data Index: 561821 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 0.5839. Min Range: -0.5839

Max Act: 0.2491. Min Act: -0.0000

Data Index: 1522001 (Python Code)

Max Activating Token Index: 923

Text #17

Max Range: 0.5839. Min Range: -0.5839

Max Act: 0.3042. Min Act: -0.0000

Data Index: 845160 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 0.5839. Min Range: -0.5839

Max Act: 0.3005. Min Act: -0.0000

Data Index: 1430189 (Python Code)

Max Activating Token Index: 824

Text #19

Max Range: 0.5839. Min Range: -0.5839

Max Act: 0.2903. Min Act: -0.0000

Data Index: 288025 (C4 (Web Text))

Max Activating Token Index: 605