Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 932 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.9598. Min Act: -0.0002

Data Index: 1610452 (Python Code)

Max Activating Token Index: 509

Text #1

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.9169. Min Act: -0.0002

Data Index: 1490964 (Python Code)

Max Activating Token Index: 483

Text #2

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.9404. Min Act: -0.0002

Data Index: 1392237 (Python Code)

Max Activating Token Index: 390

Text #3

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.8731. Min Act: -0.0002

Data Index: 1490910 (Python Code)

Max Activating Token Index: 721

Text #4

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.8927. Min Act: -0.0002

Data Index: 1646156 (Python Code)

Max Activating Token Index: 862

Text #5

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.8892. Min Act: -0.0002

Data Index: 1615449 (Python Code)

Max Activating Token Index: 674

Text #6

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.8260. Min Act: -0.0002

Data Index: 1652697 (Python Code)

Max Activating Token Index: 785

Text #7

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.8768. Min Act: -0.0002

Data Index: 1630616 (Python Code)

Max Activating Token Index: 352

Text #8

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.7968. Min Act: -0.0002

Data Index: 1436472 (Python Code)

Max Activating Token Index: 921

Text #9

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.8409. Min Act: -0.0002

Data Index: 1630607 (Python Code)

Max Activating Token Index: 133

Text #10

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.8061. Min Act: -0.0002

Data Index: 1568525 (Python Code)

Max Activating Token Index: 339

Text #11

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.7983. Min Act: -0.0002

Data Index: 1412801 (Python Code)

Max Activating Token Index: 755

Text #12

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.8408. Min Act: -0.0002

Data Index: 1364761 (Python Code)

Max Activating Token Index: 945

Text #13

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.7894. Min Act: -0.0002

Data Index: 1420996 (Python Code)

Max Activating Token Index: 336

Text #14

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.7910. Min Act: -0.0002

Data Index: 1405959 (Python Code)

Max Activating Token Index: 590

Text #15

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.7819. Min Act: -0.0002

Data Index: 1388988 (Python Code)

Max Activating Token Index: 440

Text #16

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.7644. Min Act: -0.0002

Data Index: 1533368 (Python Code)

Max Activating Token Index: 1007

Text #17

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.7273. Min Act: -0.0002

Data Index: 1364383 (Python Code)

Max Activating Token Index: 985

Text #18

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.7239. Min Act: -0.0002

Data Index: 1537465 (Python Code)

Max Activating Token Index: 606

Text #19

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.6944. Min Act: -0.0002

Data Index: 1541887 (Python Code)

Max Activating Token Index: 90