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

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

Neuron 2185 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: 4.5418. Min Range: -4.5418

Max Act: 4.5418. Min Act: -0.0000

Data Index: 1083556 (C4 (Web Text))

Max Activating Token Index: 514

Text #1

Max Range: 4.5418. Min Range: -4.5418

Max Act: 3.8904. Min Act: -0.0000

Data Index: 139448 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 4.5418. Min Range: -4.5418

Max Act: 3.3754. Min Act: -0.0000

Data Index: 146850 (C4 (Web Text))

Max Activating Token Index: 201

Text #3

Max Range: 4.5418. Min Range: -4.5418

Max Act: 3.3854. Min Act: -0.0000

Data Index: 930727 (C4 (Web Text))

Max Activating Token Index: 945

Text #4

Max Range: 4.5418. Min Range: -4.5418

Max Act: 3.8753. Min Act: -0.0000

Data Index: 1105163 (C4 (Web Text))

Max Activating Token Index: 240

Text #5

Max Range: 4.5418. Min Range: -4.5418

Max Act: 3.6837. Min Act: -0.0000

Data Index: 529697 (C4 (Web Text))

Max Activating Token Index: 587

Text #6

Max Range: 4.5418. Min Range: -4.5418

Max Act: 3.5492. Min Act: -0.0000

Data Index: 792352 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 4.5418. Min Range: -4.5418

Max Act: 2.9209. Min Act: -0.0000

Data Index: 214756 (C4 (Web Text))

Max Activating Token Index: 398

Text #8

Max Range: 4.5418. Min Range: -4.5418

Max Act: 3.5113. Min Act: -0.0000

Data Index: 838615 (C4 (Web Text))

Max Activating Token Index: 757

Text #9

Max Range: 4.5418. Min Range: -4.5418

Max Act: 3.4625. Min Act: -0.0000

Data Index: 86697 (C4 (Web Text))

Max Activating Token Index: 631

Text #10

Max Range: 4.5418. Min Range: -4.5418

Max Act: 3.4338. Min Act: -0.0000

Data Index: 318905 (C4 (Web Text))

Max Activating Token Index: 559

Text #11

Max Range: 4.5418. Min Range: -4.5418

Max Act: 3.4137. Min Act: -0.0000

Data Index: 309192 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 4.5418. Min Range: -4.5418

Max Act: 3.3407. Min Act: -0.0000

Data Index: 719086 (C4 (Web Text))

Max Activating Token Index: 689

Text #13

Max Range: 4.5418. Min Range: -4.5418

Max Act: 3.2602. Min Act: -0.0000

Data Index: 356685 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 4.5418. Min Range: -4.5418

Max Act: 3.2501. Min Act: -0.0000

Data Index: 1029727 (C4 (Web Text))

Max Activating Token Index: 479

Text #15

Max Range: 4.5418. Min Range: -4.5418

Max Act: 2.9409. Min Act: -0.0000

Data Index: 1027000 (C4 (Web Text))

Max Activating Token Index: 616

Text #16

Max Range: 4.5418. Min Range: -4.5418

Max Act: 2.9338. Min Act: -0.0000

Data Index: 35613 (C4 (Web Text))

Max Activating Token Index: 408

Text #17

Max Range: 4.5418. Min Range: -4.5418

Max Act: 2.9353. Min Act: -0.0000

Data Index: 1079389 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 4.5418. Min Range: -4.5418

Max Act: 2.8727. Min Act: -0.0000

Data Index: 1244277 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 4.5418. Min Range: -4.5418

Max Act: 3.0441. Min Act: -0.0000

Data Index: 276648 (C4 (Web Text))

Max Activating Token Index: 171