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

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

Neuron 608 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2009. Min Range: -1.2009

Max Act: 1.1887. Min Act: -0.0000

Data Index: 1351725 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 1.2009. Min Range: -1.2009

Max Act: 1.0987. Min Act: -0.0000

Data Index: 1308814 (C4 (Web Text))

Max Activating Token Index: 149

Text #2

Max Range: 1.2009. Min Range: -1.2009

Max Act: 1.0996. Min Act: -0.0000

Data Index: 591711 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 1.2009. Min Range: -1.2009

Max Act: 1.2009. Min Act: -0.0000

Data Index: 868901 (C4 (Web Text))

Max Activating Token Index: 1008

Text #4

Max Range: 1.2009. Min Range: -1.2009

Max Act: 1.0198. Min Act: -0.0000

Data Index: 439857 (C4 (Web Text))

Max Activating Token Index: 221

Text #5

Max Range: 1.2009. Min Range: -1.2009

Max Act: 1.0362. Min Act: -0.0000

Data Index: 1412052 (Python Code)

Max Activating Token Index: 993

Text #6

Max Range: 1.2009. Min Range: -1.2009

Max Act: 0.9930. Min Act: -0.0000

Data Index: 1119126 (C4 (Web Text))

Max Activating Token Index: 545

Text #7

Max Range: 1.2009. Min Range: -1.2009

Max Act: 0.9620. Min Act: -0.0000

Data Index: 789363 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 1.2009. Min Range: -1.2009

Max Act: 0.9505. Min Act: -0.0000

Data Index: 892636 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 1.2009. Min Range: -1.2009

Max Act: 1.0117. Min Act: -0.0000

Data Index: 1130329 (C4 (Web Text))

Max Activating Token Index: 600

Text #10

Max Range: 1.2009. Min Range: -1.2009

Max Act: 0.9646. Min Act: -0.0000

Data Index: 489863 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 1.2009. Min Range: -1.2009

Max Act: 0.9452. Min Act: -0.0000

Data Index: 1505913 (Python Code)

Max Activating Token Index: 645

Text #12

Max Range: 1.2009. Min Range: -1.2009

Max Act: 0.9224. Min Act: -0.0000

Data Index: 15655 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 1.2009. Min Range: -1.2009

Max Act: 0.8103. Min Act: -0.0000

Data Index: 398011 (C4 (Web Text))

Max Activating Token Index: 830

Text #14

Max Range: 1.2009. Min Range: -1.2009

Max Act: 0.8956. Min Act: -0.0000

Data Index: 1385110 (Python Code)

Max Activating Token Index: 856

Text #15

Max Range: 1.2009. Min Range: -1.2009

Max Act: 0.9630. Min Act: -0.0000

Data Index: 1376981 (Python Code)

Max Activating Token Index: 260

Text #16

Max Range: 1.2009. Min Range: -1.2009

Max Act: 0.9334. Min Act: -0.0000

Data Index: 716111 (C4 (Web Text))

Max Activating Token Index: 719

Text #17

Max Range: 1.2009. Min Range: -1.2009

Max Act: 0.9675. Min Act: -0.0000

Data Index: 592010 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 1.2009. Min Range: -1.2009

Max Act: 0.9308. Min Act: -0.0000

Data Index: 658170 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 1.2009. Min Range: -1.2009

Max Act: 0.9034. Min Act: -0.0000

Data Index: 1225481 (C4 (Web Text))

Max Activating Token Index: 601