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

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

Neuron 3492 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: 0.0730. Min Range: -0.0730

Max Act: 0.0730. Min Act: -0.0002

Data Index: 1077147 (C4 (Web Text))

Max Activating Token Index: 258

Text #1

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0650. Min Act: -0.0002

Data Index: 399848 (C4 (Web Text))

Max Activating Token Index: 328

Text #2

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0672. Min Act: -0.0002

Data Index: 827856 (C4 (Web Text))

Max Activating Token Index: 935

Text #3

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0601. Min Act: -0.0002

Data Index: 420811 (C4 (Web Text))

Max Activating Token Index: 635

Text #4

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0574. Min Act: -0.0002

Data Index: 310625 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0622. Min Act: -0.0002

Data Index: 492805 (C4 (Web Text))

Max Activating Token Index: 589

Text #6

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0519. Min Act: -0.0002

Data Index: 450415 (C4 (Web Text))

Max Activating Token Index: 247

Text #7

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0569. Min Act: -0.0002

Data Index: 161317 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0652. Min Act: -0.0002

Data Index: 1232216 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1214910 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0466. Min Act: -0.0002

Data Index: 1562052 (Python Code)

Max Activating Token Index: 829

Text #11

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0636. Min Act: -0.0002

Data Index: 1090968 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0491. Min Act: -0.0002

Data Index: 52148 (C4 (Web Text))

Max Activating Token Index: 952

Text #13

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0478. Min Act: -0.0002

Data Index: 1475133 (Python Code)

Max Activating Token Index: 777

Text #14

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0550. Min Act: -0.0002

Data Index: 646788 (C4 (Web Text))

Max Activating Token Index: 229

Text #15

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0505. Min Act: -0.0002

Data Index: 57610 (C4 (Web Text))

Max Activating Token Index: 904

Text #16

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0512. Min Act: -0.0002

Data Index: 467526 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0614. Min Act: -0.0002

Data Index: 1318222 (C4 (Web Text))

Max Activating Token Index: 325

Text #18

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0537. Min Act: -0.0002

Data Index: 1298737 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0513. Min Act: -0.0002

Data Index: 78652 (C4 (Web Text))

Max Activating Token Index: 877