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

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

Neuron 2918 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0492. Min Act: -0.0004

Data Index: 1009269 (C4 (Web Text))

Max Activating Token Index: 686

Text #1

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0491. Min Act: -0.0004

Data Index: 155136 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0512. Min Act: -0.0004

Data Index: 435790 (C4 (Web Text))

Max Activating Token Index: 856

Text #3

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0515. Min Act: -0.0004

Data Index: 758968 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0500. Min Act: -0.0004

Data Index: 73092 (C4 (Web Text))

Max Activating Token Index: 971

Text #5

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0528. Min Act: -0.0004

Data Index: 834529 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0539. Min Act: -0.0004

Data Index: 740811 (C4 (Web Text))

Max Activating Token Index: 433

Text #7

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0558. Min Act: -0.0004

Data Index: 620653 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0487. Min Act: -0.0004

Data Index: 998124 (C4 (Web Text))

Max Activating Token Index: 441

Text #9

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0523. Min Act: -0.0004

Data Index: 696715 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0473. Min Act: -0.0004

Data Index: 118606 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0493. Min Act: -0.0004

Data Index: 1063168 (C4 (Web Text))

Max Activating Token Index: 683

Text #12

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0482. Min Act: -0.0004

Data Index: 1251991 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0500. Min Act: -0.0004

Data Index: 1252083 (C4 (Web Text))

Max Activating Token Index: 951

Text #14

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0476. Min Act: -0.0004

Data Index: 477833 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0451. Min Act: -0.0004

Data Index: 1098651 (C4 (Web Text))

Max Activating Token Index: 1004

Text #16

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0494. Min Act: -0.0004

Data Index: 90371 (C4 (Web Text))

Max Activating Token Index: 147

Text #17

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0524. Min Act: -0.0004

Data Index: 775990 (C4 (Web Text))

Max Activating Token Index: 961

Text #18

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0420. Min Act: -0.0004

Data Index: 1033254 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0489. Min Act: -0.0004

Data Index: 482917 (C4 (Web Text))

Max Activating Token Index: 437