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

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

Neuron 3564 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: 0.0952. Min Range: -0.0952

Max Act: 0.0932. Min Act: -0.0002

Data Index: 836429 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0952. Min Act: -0.0002

Data Index: 430102 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0803. Min Act: -0.0002

Data Index: 523477 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0825. Min Act: -0.0002

Data Index: 1036735 (C4 (Web Text))

Max Activating Token Index: 274

Text #4

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0861. Min Act: -0.0002

Data Index: 1118311 (C4 (Web Text))

Max Activating Token Index: 777

Text #5

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0804. Min Act: -0.0002

Data Index: 603050 (C4 (Web Text))

Max Activating Token Index: 244

Text #6

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0802. Min Act: -0.0002

Data Index: 470826 (C4 (Web Text))

Max Activating Token Index: 1011

Text #7

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0775. Min Act: -0.0002

Data Index: 526549 (C4 (Web Text))

Max Activating Token Index: 380

Text #8

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0708. Min Act: -0.0002

Data Index: 335685 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0785. Min Act: -0.0002

Data Index: 598840 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0715. Min Act: -0.0002

Data Index: 400639 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0851. Min Act: -0.0002

Data Index: 554982 (C4 (Web Text))

Max Activating Token Index: 225

Text #12

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0688. Min Act: -0.0002

Data Index: 792502 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0585. Min Act: -0.0002

Data Index: 190751 (C4 (Web Text))

Max Activating Token Index: 937

Text #14

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0560. Min Act: -0.0002

Data Index: 393271 (C4 (Web Text))

Max Activating Token Index: 123

Text #15

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0594. Min Act: -0.0002

Data Index: 1311224 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0691. Min Act: -0.0002

Data Index: 579656 (C4 (Web Text))

Max Activating Token Index: 423

Text #17

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0550. Min Act: -0.0002

Data Index: 133318 (C4 (Web Text))

Max Activating Token Index: 326

Text #18

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0654. Min Act: -0.0002

Data Index: 286353 (C4 (Web Text))

Max Activating Token Index: 391

Text #19

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0611. Min Act: -0.0002

Data Index: 430541 (C4 (Web Text))

Max Activating Token Index: 283