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

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

Neuron 1504 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: 1.7625. Min Range: -1.7625

Max Act: 1.7087. Min Act: -0.0000

Data Index: 1553794 (Python Code)

Max Activating Token Index: 158

Text #1

Max Range: 1.7625. Min Range: -1.7625

Max Act: 1.7568. Min Act: -0.0000

Data Index: 1453294 (Python Code)

Max Activating Token Index: 677

Text #2

Max Range: 1.7625. Min Range: -1.7625

Max Act: 1.7317. Min Act: -0.0000

Data Index: 1495492 (Python Code)

Max Activating Token Index: 404

Text #3

Max Range: 1.7625. Min Range: -1.7625

Max Act: 1.6609. Min Act: -0.0000

Data Index: 1485127 (Python Code)

Max Activating Token Index: 675

Text #4

Max Range: 1.7625. Min Range: -1.7625

Max Act: 1.4467. Min Act: -0.0000

Data Index: 1508762 (Python Code)

Max Activating Token Index: 899

Text #5

Max Range: 1.7625. Min Range: -1.7625

Max Act: 1.3639. Min Act: -0.0000

Data Index: 1484248 (Python Code)

Max Activating Token Index: 842

Text #6

Max Range: 1.7625. Min Range: -1.7625

Max Act: 1.6168. Min Act: -0.0000

Data Index: 1612134 (Python Code)

Max Activating Token Index: 323

Text #7

Max Range: 1.7625. Min Range: -1.7625

Max Act: 1.3932. Min Act: -0.0000

Data Index: 1486296 (Python Code)

Max Activating Token Index: 433

Text #8

Max Range: 1.7625. Min Range: -1.7625

Max Act: 1.7625. Min Act: -0.0000

Data Index: 1495742 (Python Code)

Max Activating Token Index: 937

Text #9

Max Range: 1.7625. Min Range: -1.7625

Max Act: 1.2902. Min Act: -0.0000

Data Index: 1615426 (Python Code)

Max Activating Token Index: 581

Text #10

Max Range: 1.7625. Min Range: -1.7625

Max Act: 1.2726. Min Act: -0.0000

Data Index: 1577459 (Python Code)

Max Activating Token Index: 232

Text #11

Max Range: 1.7625. Min Range: -1.7625

Max Act: 1.3369. Min Act: -0.0000

Data Index: 1494316 (Python Code)

Max Activating Token Index: 274

Text #12

Max Range: 1.7625. Min Range: -1.7625

Max Act: 1.3132. Min Act: -0.0000

Data Index: 1531393 (Python Code)

Max Activating Token Index: 369

Text #13

Max Range: 1.7625. Min Range: -1.7625

Max Act: 1.2173. Min Act: -0.0000

Data Index: 1436045 (Python Code)

Max Activating Token Index: 173

Text #14

Max Range: 1.7625. Min Range: -1.7625

Max Act: 1.2590. Min Act: -0.0000

Data Index: 1492093 (Python Code)

Max Activating Token Index: 479

Text #15

Max Range: 1.7625. Min Range: -1.7625

Max Act: 1.2747. Min Act: -0.0000

Data Index: 1634944 (Python Code)

Max Activating Token Index: 974

Text #16

Max Range: 1.7625. Min Range: -1.7625

Max Act: 1.1890. Min Act: -0.0000

Data Index: 1606952 (Python Code)

Max Activating Token Index: 677

Text #17

Max Range: 1.7625. Min Range: -1.7625

Max Act: 1.3701. Min Act: -0.0000

Data Index: 1622200 (Python Code)

Max Activating Token Index: 162

Text #18

Max Range: 1.7625. Min Range: -1.7625

Max Act: 1.2813. Min Act: -0.0000

Data Index: 1375798 (Python Code)

Max Activating Token Index: 464

Text #19

Max Range: 1.7625. Min Range: -1.7625

Max Act: 1.2877. Min Act: -0.0000

Data Index: 1363234 (Python Code)

Max Activating Token Index: 269