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

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

Neuron 4423 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9693. Min Range: -0.9693

Max Act: 0.9693. Min Act: -0.0000

Data Index: 507029 (C4 (Web Text))

Max Activating Token Index: 698

Text #1

Max Range: 0.9693. Min Range: -0.9693

Max Act: 0.7526. Min Act: -0.0000

Data Index: 689392 (C4 (Web Text))

Max Activating Token Index: 290

Text #2

Max Range: 0.9693. Min Range: -0.9693

Max Act: 0.7138. Min Act: 0.0001

Data Index: 1011515 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 0.9693. Min Range: -0.9693

Max Act: 0.6441. Min Act: 0.0002

Data Index: 1230743 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 0.9693. Min Range: -0.9693

Max Act: 0.6661. Min Act: -0.0000

Data Index: 314083 (C4 (Web Text))

Max Activating Token Index: 566

Text #5

Max Range: 0.9693. Min Range: -0.9693

Max Act: 0.6209. Min Act: -0.0000

Data Index: 667563 (C4 (Web Text))

Max Activating Token Index: 981

Text #6

Max Range: 0.9693. Min Range: -0.9693

Max Act: 0.6472. Min Act: 0.0000

Data Index: 207923 (C4 (Web Text))

Max Activating Token Index: 460

Text #7

Max Range: 0.9693. Min Range: -0.9693

Max Act: 0.6295. Min Act: -0.0000

Data Index: 1235635 (C4 (Web Text))

Max Activating Token Index: 582

Text #8

Max Range: 0.9693. Min Range: -0.9693

Max Act: 0.6277. Min Act: -0.0000

Data Index: 904174 (C4 (Web Text))

Max Activating Token Index: 68

Text #9

Max Range: 0.9693. Min Range: -0.9693

Max Act: 0.6130. Min Act: -0.0000

Data Index: 1078242 (C4 (Web Text))

Max Activating Token Index: 314

Text #10

Max Range: 0.9693. Min Range: -0.9693

Max Act: 0.6478. Min Act: 0.0000

Data Index: 245708 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 0.9693. Min Range: -0.9693

Max Act: 0.5770. Min Act: -0.0000

Data Index: 517256 (C4 (Web Text))

Max Activating Token Index: 895

Text #12

Max Range: 0.9693. Min Range: -0.9693

Max Act: 0.5892. Min Act: -0.0000

Data Index: 703383 (C4 (Web Text))

Max Activating Token Index: 900

Text #13

Max Range: 0.9693. Min Range: -0.9693

Max Act: 0.5860. Min Act: -0.0000

Data Index: 182538 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 0.9693. Min Range: -0.9693

Max Act: 0.5508. Min Act: -0.0000

Data Index: 545643 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 0.9693. Min Range: -0.9693

Max Act: 0.5590. Min Act: -0.0000

Data Index: 196355 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 0.9693. Min Range: -0.9693

Max Act: 0.5664. Min Act: -0.0000

Data Index: 459268 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 0.9693. Min Range: -0.9693

Max Act: 0.5736. Min Act: -0.0000

Data Index: 370771 (C4 (Web Text))

Max Activating Token Index: 459

Text #18

Max Range: 0.9693. Min Range: -0.9693

Max Act: 0.5665. Min Act: -0.0000

Data Index: 756158 (C4 (Web Text))

Max Activating Token Index: 186

Text #19

Max Range: 0.9693. Min Range: -0.9693

Max Act: 0.5724. Min Act: -0.0000

Data Index: 780592 (C4 (Web Text))

Max Activating Token Index: 948