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

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

Neuron 4264 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8344. Min Range: -0.8344

Max Act: 0.8085. Min Act: -0.0003

Data Index: 64222 (C4 (Web Text))

Max Activating Token Index: 336

Text #1

Max Range: 0.8344. Min Range: -0.8344

Max Act: 0.8344. Min Act: -0.0003

Data Index: 463312 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 0.8344. Min Range: -0.8344

Max Act: 0.7690. Min Act: -0.0003

Data Index: 1187497 (C4 (Web Text))

Max Activating Token Index: 732

Text #3

Max Range: 0.8344. Min Range: -0.8344

Max Act: 0.7861. Min Act: -0.0002

Data Index: 71615 (C4 (Web Text))

Max Activating Token Index: 416

Text #4

Max Range: 0.8344. Min Range: -0.8344

Max Act: 0.7369. Min Act: -0.0003

Data Index: 884583 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 0.8344. Min Range: -0.8344

Max Act: 0.7473. Min Act: -0.0002

Data Index: 405678 (C4 (Web Text))

Max Activating Token Index: 400

Text #6

Max Range: 0.8344. Min Range: -0.8344

Max Act: 0.7418. Min Act: -0.0003

Data Index: 1289478 (C4 (Web Text))

Max Activating Token Index: 247

Text #7

Max Range: 0.8344. Min Range: -0.8344

Max Act: 0.7602. Min Act: -0.0002

Data Index: 1195564 (C4 (Web Text))

Max Activating Token Index: 360

Text #8

Max Range: 0.8344. Min Range: -0.8344

Max Act: 0.7555. Min Act: -0.0003

Data Index: 832973 (C4 (Web Text))

Max Activating Token Index: 1006

Text #9

Max Range: 0.8344. Min Range: -0.8344

Max Act: 0.6917. Min Act: -0.0003

Data Index: 481922 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 0.8344. Min Range: -0.8344

Max Act: 0.7087. Min Act: -0.0003

Data Index: 1228969 (C4 (Web Text))

Max Activating Token Index: 954

Text #11

Max Range: 0.8344. Min Range: -0.8344

Max Act: 0.6849. Min Act: -0.0003

Data Index: 333396 (C4 (Web Text))

Max Activating Token Index: 420

Text #12

Max Range: 0.8344. Min Range: -0.8344

Max Act: 0.7051. Min Act: -0.0003

Data Index: 390947 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 0.8344. Min Range: -0.8344

Max Act: 0.6961. Min Act: -0.0002

Data Index: 787855 (C4 (Web Text))

Max Activating Token Index: 405

Text #14

Max Range: 0.8344. Min Range: -0.8344

Max Act: 0.6943. Min Act: -0.0003

Data Index: 118769 (C4 (Web Text))

Max Activating Token Index: 933

Text #15

Max Range: 0.8344. Min Range: -0.8344

Max Act: 0.6871. Min Act: -0.0003

Data Index: 628036 (C4 (Web Text))

Max Activating Token Index: 173

Text #16

Max Range: 0.8344. Min Range: -0.8344

Max Act: 0.6836. Min Act: -0.0003

Data Index: 199426 (C4 (Web Text))

Max Activating Token Index: 915

Text #17

Max Range: 0.8344. Min Range: -0.8344

Max Act: 0.6810. Min Act: -0.0003

Data Index: 250840 (C4 (Web Text))

Max Activating Token Index: 521

Text #18

Max Range: 0.8344. Min Range: -0.8344

Max Act: 0.6796. Min Act: -0.0003

Data Index: 377511 (C4 (Web Text))

Max Activating Token Index: 953

Text #19

Max Range: 0.8344. Min Range: -0.8344

Max Act: 0.6692. Min Act: -0.0003

Data Index: 10659 (C4 (Web Text))

Max Activating Token Index: 209