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

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

Neuron 5065 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: 0.0700. Min Range: -0.0700

Max Act: 0.0700. Min Act: -0.0000

Data Index: 58991 (C4 (Web Text))

Max Activating Token Index: 920

Text #1

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0646. Min Act: -0.0000

Data Index: 808750 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0614. Min Act: 0.0000

Data Index: 533961 (C4 (Web Text))

Max Activating Token Index: 774

Text #3

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0607. Min Act: 0.0000

Data Index: 1034102 (C4 (Web Text))

Max Activating Token Index: 315

Text #4

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0581. Min Act: 0.0000

Data Index: 875335 (C4 (Web Text))

Max Activating Token Index: 722

Text #5

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0596. Min Act: -0.0000

Data Index: 541983 (C4 (Web Text))

Max Activating Token Index: 830

Text #6

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0583. Min Act: 0.0000

Data Index: 329356 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0567. Min Act: -0.0000

Data Index: 1398856 (Python Code)

Max Activating Token Index: 231

Text #8

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0583. Min Act: 0.0000

Data Index: 1157379 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0591. Min Act: -0.0000

Data Index: 632094 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0621. Min Act: -0.0000

Data Index: 312734 (C4 (Web Text))

Max Activating Token Index: 648

Text #11

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0582. Min Act: 0.0000

Data Index: 1262195 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0576. Min Act: -0.0000

Data Index: 206377 (C4 (Web Text))

Max Activating Token Index: 886

Text #13

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0574. Min Act: 0.0000

Data Index: 620455 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0552. Min Act: 0.0000

Data Index: 112090 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0566. Min Act: -0.0000

Data Index: 1188821 (C4 (Web Text))

Max Activating Token Index: 985

Text #16

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0561. Min Act: -0.0000

Data Index: 582007 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0541. Min Act: -0.0000

Data Index: 796140 (C4 (Web Text))

Max Activating Token Index: 812

Text #18

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0539. Min Act: 0.0000

Data Index: 727982 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0551. Min Act: -0.0000

Data Index: 80968 (C4 (Web Text))

Max Activating Token Index: 464