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

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

Neuron 3564 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.8028. Min Act: -0.0000

Data Index: 1339911 (C4 (Web Text))

Max Activating Token Index: 504

Text #1

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.7331. Min Act: -0.0000

Data Index: 252469 (C4 (Web Text))

Max Activating Token Index: 925

Text #2

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.6111. Min Act: -0.0000

Data Index: 946201 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.6049. Min Act: -0.0000

Data Index: 1337276 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.5265. Min Act: -0.0000

Data Index: 1161985 (C4 (Web Text))

Max Activating Token Index: 531

Text #5

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.4803. Min Act: -0.0000

Data Index: 1515886 (Python Code)

Max Activating Token Index: 861

Text #6

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.3253. Min Act: -0.0000

Data Index: 1571795 (Python Code)

Max Activating Token Index: 966

Text #7

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.4590. Min Act: -0.0000

Data Index: 990917 (C4 (Web Text))

Max Activating Token Index: 10

Text #8

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.4445. Min Act: -0.0000

Data Index: 1388701 (Python Code)

Max Activating Token Index: 892

Text #9

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.4599. Min Act: -0.0000

Data Index: 732702 (C4 (Web Text))

Max Activating Token Index: 167

Text #10

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.4384. Min Act: -0.0000

Data Index: 790053 (C4 (Web Text))

Max Activating Token Index: 944

Text #11

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.4273. Min Act: -0.0000

Data Index: 1038058 (C4 (Web Text))

Max Activating Token Index: 96

Text #12

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.3323. Min Act: -0.0000

Data Index: 106313 (C4 (Web Text))

Max Activating Token Index: 878

Text #13

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.3747. Min Act: -0.0000

Data Index: 239688 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.3294. Min Act: -0.0000

Data Index: 719790 (C4 (Web Text))

Max Activating Token Index: 879

Text #15

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.3831. Min Act: -0.0000

Data Index: 863811 (C4 (Web Text))

Max Activating Token Index: 5

Text #16

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.3708. Min Act: -0.0000

Data Index: 247040 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.3720. Min Act: -0.0000

Data Index: 872615 (C4 (Web Text))

Max Activating Token Index: 916

Text #18

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.3623. Min Act: -0.0000

Data Index: 1446431 (Python Code)

Max Activating Token Index: 16

Text #19

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.3325. Min Act: -0.0000

Data Index: 1097365 (C4 (Web Text))

Max Activating Token Index: 874