Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3866 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8578. Min Range: -1.8578

Max Act: 1.8285. Min Act: -0.0002

Data Index: 1001518 (C4 (Web Text))

Max Activating Token Index: 667

Text #1

Max Range: 1.8578. Min Range: -1.8578

Max Act: 1.8578. Min Act: -0.0002

Data Index: 300784 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 1.8578. Min Range: -1.8578

Max Act: 1.7425. Min Act: -0.0002

Data Index: 161228 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 1.8578. Min Range: -1.8578

Max Act: 1.7861. Min Act: -0.0001

Data Index: 1290944 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 1.8578. Min Range: -1.8578

Max Act: 1.7534. Min Act: -0.0001

Data Index: 677492 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 1.8578. Min Range: -1.8578

Max Act: 1.7876. Min Act: -0.0002

Data Index: 838527 (C4 (Web Text))

Max Activating Token Index: 481

Text #6

Max Range: 1.8578. Min Range: -1.8578

Max Act: 1.6083. Min Act: -0.0001

Data Index: 740551 (C4 (Web Text))

Max Activating Token Index: 761

Text #7

Max Range: 1.8578. Min Range: -1.8578

Max Act: 1.7068. Min Act: -0.0002

Data Index: 847283 (C4 (Web Text))

Max Activating Token Index: 569

Text #8

Max Range: 1.8578. Min Range: -1.8578

Max Act: 1.6889. Min Act: -0.0002

Data Index: 32334 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 1.8578. Min Range: -1.8578

Max Act: 1.6073. Min Act: -0.0001

Data Index: 995658 (C4 (Web Text))

Max Activating Token Index: 457

Text #10

Max Range: 1.8578. Min Range: -1.8578

Max Act: 1.7220. Min Act: -0.0001

Data Index: 987611 (C4 (Web Text))

Max Activating Token Index: 413

Text #11

Max Range: 1.8578. Min Range: -1.8578

Max Act: 1.7130. Min Act: -0.0001

Data Index: 539046 (C4 (Web Text))

Max Activating Token Index: 402

Text #12

Max Range: 1.8578. Min Range: -1.8578

Max Act: 1.5261. Min Act: -0.0002

Data Index: 1349544 (C4 (Web Text))

Max Activating Token Index: 618

Text #13

Max Range: 1.8578. Min Range: -1.8578

Max Act: 1.5887. Min Act: -0.0002

Data Index: 991597 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 1.8578. Min Range: -1.8578

Max Act: 1.5656. Min Act: -0.0001

Data Index: 860769 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 1.8578. Min Range: -1.8578

Max Act: 1.5751. Min Act: -0.0001

Data Index: 896448 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 1.8578. Min Range: -1.8578

Max Act: 1.6113. Min Act: -0.0002

Data Index: 193699 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 1.8578. Min Range: -1.8578

Max Act: 1.5608. Min Act: -0.0001

Data Index: 772145 (C4 (Web Text))

Max Activating Token Index: 897

Text #18

Max Range: 1.8578. Min Range: -1.8578

Max Act: 1.6153. Min Act: -0.0002

Data Index: 1029753 (C4 (Web Text))

Max Activating Token Index: 887

Text #19

Max Range: 1.8578. Min Range: -1.8578

Max Act: 1.6434. Min Act: -0.0002

Data Index: 566135 (C4 (Web Text))

Max Activating Token Index: 404