Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 340 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0924. Min Act: -0.0001

Data Index: 420967 (C4 (Web Text))

Max Activating Token Index: 505

Text #1

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0877. Min Act: -0.0001

Data Index: 1100473 (C4 (Web Text))

Max Activating Token Index: 465

Text #2

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0852. Min Act: -0.0001

Data Index: 1107280 (C4 (Web Text))

Max Activating Token Index: 709

Text #3

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0815. Min Act: -0.0001

Data Index: 705753 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0709. Min Act: -0.0001

Data Index: 1192143 (C4 (Web Text))

Max Activating Token Index: 621

Text #5

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0784. Min Act: -0.0001

Data Index: 937817 (C4 (Web Text))

Max Activating Token Index: 572

Text #6

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0855. Min Act: -0.0001

Data Index: 827410 (C4 (Web Text))

Max Activating Token Index: 898

Text #7

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0784. Min Act: -0.0001

Data Index: 702070 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0785. Min Act: -0.0001

Data Index: 258376 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0836. Min Act: -0.0001

Data Index: 146698 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0762. Min Act: -0.0001

Data Index: 496518 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0785. Min Act: -0.0001

Data Index: 3382 (C4 (Web Text))

Max Activating Token Index: 99

Text #12

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0782. Min Act: -0.0001

Data Index: 733283 (C4 (Web Text))

Max Activating Token Index: 146

Text #13

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0799. Min Act: -0.0001

Data Index: 1252044 (C4 (Web Text))

Max Activating Token Index: 993

Text #14

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0750. Min Act: -0.0001

Data Index: 122764 (C4 (Web Text))

Max Activating Token Index: 820

Text #15

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0776. Min Act: -0.0001

Data Index: 947034 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0769. Min Act: -0.0000

Data Index: 418033 (C4 (Web Text))

Max Activating Token Index: 669

Text #17

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0814. Min Act: -0.0001

Data Index: 1167216 (C4 (Web Text))

Max Activating Token Index: 669

Text #18

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0748. Min Act: -0.0000

Data Index: 1316633 (C4 (Web Text))

Max Activating Token Index: 846

Text #19

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0776. Min Act: -0.0001

Data Index: 1056340 (C4 (Web Text))

Max Activating Token Index: 1013