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

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

Neuron 5539 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0778. Min Act: -0.0002

Data Index: 753688 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0747. Min Act: -0.0002

Data Index: 769592 (C4 (Web Text))

Max Activating Token Index: 616

Text #2

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0738. Min Act: -0.0002

Data Index: 821103 (C4 (Web Text))

Max Activating Token Index: 532

Text #3

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0668. Min Act: -0.0002

Data Index: 1161469 (C4 (Web Text))

Max Activating Token Index: 640

Text #4

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0609. Min Act: -0.0002

Data Index: 1241107 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0606. Min Act: -0.0002

Data Index: 369890 (C4 (Web Text))

Max Activating Token Index: 407

Text #6

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0615. Min Act: -0.0002

Data Index: 112776 (C4 (Web Text))

Max Activating Token Index: 592

Text #7

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0588. Min Act: -0.0002

Data Index: 996639 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0574. Min Act: -0.0002

Data Index: 1003111 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0551. Min Act: -0.0002

Data Index: 1274330 (C4 (Web Text))

Max Activating Token Index: 102

Text #10

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0566. Min Act: -0.0002

Data Index: 1330679 (C4 (Web Text))

Max Activating Token Index: 503

Text #11

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0520. Min Act: -0.0002

Data Index: 440939 (C4 (Web Text))

Max Activating Token Index: 590

Text #12

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0543. Min Act: -0.0002

Data Index: 556430 (C4 (Web Text))

Max Activating Token Index: 410

Text #13

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0540. Min Act: -0.0002

Data Index: 170304 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0538. Min Act: -0.0002

Data Index: 482677 (C4 (Web Text))

Max Activating Token Index: 696

Text #15

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0514. Min Act: -0.0002

Data Index: 1193849 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0531. Min Act: -0.0002

Data Index: 280699 (C4 (Web Text))

Max Activating Token Index: 820

Text #17

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0529. Min Act: -0.0002

Data Index: 671315 (C4 (Web Text))

Max Activating Token Index: 219

Text #18

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0524. Min Act: -0.0002

Data Index: 202650 (C4 (Web Text))

Max Activating Token Index: 74

Text #19

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0520. Min Act: -0.0002

Data Index: 511985 (C4 (Web Text))

Max Activating Token Index: 255