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

Dataset: The Pile

Neuron 3224 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.7250. Min Act: -0.0000

Data Index: 25760 (The Pile)

Max Activating Token Index: 264

Text #1

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.7157. Min Act: -0.0000

Data Index: 612396 (The Pile)

Max Activating Token Index: 372

Text #2

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.6869. Min Act: -0.0000

Data Index: 31488 (The Pile)

Max Activating Token Index: 616

Text #3

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.6562. Min Act: -0.0000

Data Index: 660930 (The Pile)

Max Activating Token Index: 176

Text #4

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.6592. Min Act: -0.0000

Data Index: 205902 (The Pile)

Max Activating Token Index: 430

Text #5

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.6612. Min Act: -0.0000

Data Index: 1330032 (The Pile)

Max Activating Token Index: 161

Text #6

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.6203. Min Act: -0.0000

Data Index: 1308176 (The Pile)

Max Activating Token Index: 787

Text #7

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.5942. Min Act: -0.0000

Data Index: 311417 (The Pile)

Max Activating Token Index: 91

Text #8

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.6265. Min Act: -0.0000

Data Index: 832730 (The Pile)

Max Activating Token Index: 115

Text #9

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.6039. Min Act: -0.0000

Data Index: 381781 (The Pile)

Max Activating Token Index: 362

Text #10

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.6456. Min Act: -0.0000

Data Index: 1925364 (The Pile)

Max Activating Token Index: 763

Text #11

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.5641. Min Act: -0.0000

Data Index: 612648 (The Pile)

Max Activating Token Index: 729

Text #12

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.6019. Min Act: -0.0000

Data Index: 1852574 (The Pile)

Max Activating Token Index: 976

Text #13

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.6007. Min Act: -0.0000

Data Index: 923976 (The Pile)

Max Activating Token Index: 289

Text #14

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.6156. Min Act: -0.0000

Data Index: 1713062 (The Pile)

Max Activating Token Index: 212

Text #15

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.5926. Min Act: -0.0000

Data Index: 1931692 (The Pile)

Max Activating Token Index: 174

Text #16

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.5877. Min Act: -0.0000

Data Index: 872071 (The Pile)

Max Activating Token Index: 589

Text #17

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.5675. Min Act: -0.0000

Data Index: 321118 (The Pile)

Max Activating Token Index: 477

Text #18

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.5995. Min Act: -0.0000

Data Index: 1772802 (The Pile)

Max Activating Token Index: 137

Text #19

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.5796. Min Act: -0.0000

Data Index: 642095 (The Pile)

Max Activating Token Index: 976