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

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

Neuron 36 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.9857. Min Act: -0.0001

Data Index: 1570390 (Python Code)

Max Activating Token Index: 417

Text #1

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.9088. Min Act: -0.0000

Data Index: 1503677 (Python Code)

Max Activating Token Index: 189

Text #2

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.8914. Min Act: -0.0001

Data Index: 1524758 (Python Code)

Max Activating Token Index: 651

Text #3

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.8943. Min Act: -0.0000

Data Index: 1522950 (Python Code)

Max Activating Token Index: 422

Text #4

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.8964. Min Act: -0.0000

Data Index: 1578211 (Python Code)

Max Activating Token Index: 841

Text #5

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.8431. Min Act: -0.0001

Data Index: 1459215 (Python Code)

Max Activating Token Index: 842

Text #6

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.8329. Min Act: -0.0000

Data Index: 1470450 (Python Code)

Max Activating Token Index: 173

Text #7

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.7419. Min Act: -0.0000

Data Index: 1377925 (Python Code)

Max Activating Token Index: 213

Text #8

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.8091. Min Act: -0.0000

Data Index: 1618096 (Python Code)

Max Activating Token Index: 201

Text #9

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.8232. Min Act: -0.0000

Data Index: 1501324 (Python Code)

Max Activating Token Index: 578

Text #10

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.8061. Min Act: -0.0000

Data Index: 1362498 (Python Code)

Max Activating Token Index: 454

Text #11

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.7870. Min Act: -0.0000

Data Index: 1415730 (Python Code)

Max Activating Token Index: 264

Text #12

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.7786. Min Act: -0.0000

Data Index: 1550612 (Python Code)

Max Activating Token Index: 618

Text #13

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.7669. Min Act: -0.0000

Data Index: 1652073 (Python Code)

Max Activating Token Index: 501

Text #14

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.8199. Min Act: -0.0000

Data Index: 1609187 (Python Code)

Max Activating Token Index: 658

Text #15

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.7420. Min Act: -0.0000

Data Index: 1542526 (Python Code)

Max Activating Token Index: 376

Text #16

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.7532. Min Act: -0.0000

Data Index: 1610701 (Python Code)

Max Activating Token Index: 168

Text #17

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.7649. Min Act: -0.0000

Data Index: 1584617 (Python Code)

Max Activating Token Index: 925

Text #18

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.8154. Min Act: -0.0000

Data Index: 1545917 (Python Code)

Max Activating Token Index: 163

Text #19

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.7939. Min Act: -0.0000

Data Index: 1522592 (Python Code)

Max Activating Token Index: 775