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

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

Neuron 1628 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6405. Min Range: -0.6405

Max Act: 0.5830. Min Act: -0.0000

Data Index: 1186068 (C4 (Web Text))

Max Activating Token Index: 464

Text #1

Max Range: 0.6405. Min Range: -0.6405

Max Act: 0.6405. Min Act: -0.0000

Data Index: 26604 (C4 (Web Text))

Max Activating Token Index: 913

Text #2

Max Range: 0.6405. Min Range: -0.6405

Max Act: 0.5777. Min Act: -0.0000

Data Index: 920305 (C4 (Web Text))

Max Activating Token Index: 868

Text #3

Max Range: 0.6405. Min Range: -0.6405

Max Act: 0.5595. Min Act: -0.0000

Data Index: 1335037 (C4 (Web Text))

Max Activating Token Index: 550

Text #4

Max Range: 0.6405. Min Range: -0.6405

Max Act: 0.5679. Min Act: -0.0000

Data Index: 584257 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 0.6405. Min Range: -0.6405

Max Act: 0.5116. Min Act: -0.0000

Data Index: 1268739 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 0.6405. Min Range: -0.6405

Max Act: 0.5162. Min Act: -0.0000

Data Index: 881279 (C4 (Web Text))

Max Activating Token Index: 887

Text #7

Max Range: 0.6405. Min Range: -0.6405

Max Act: 0.5146. Min Act: -0.0000

Data Index: 1350239 (C4 (Web Text))

Max Activating Token Index: 312

Text #8

Max Range: 0.6405. Min Range: -0.6405

Max Act: 0.4752. Min Act: -0.0000

Data Index: 1354969 (C4 (Web Text))

Max Activating Token Index: 680

Text #9

Max Range: 0.6405. Min Range: -0.6405

Max Act: 0.4824. Min Act: -0.0000

Data Index: 199256 (C4 (Web Text))

Max Activating Token Index: 467

Text #10

Max Range: 0.6405. Min Range: -0.6405

Max Act: 0.5045. Min Act: -0.0000

Data Index: 612901 (C4 (Web Text))

Max Activating Token Index: 564

Text #11

Max Range: 0.6405. Min Range: -0.6405

Max Act: 0.5077. Min Act: -0.0000

Data Index: 1095887 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 0.6405. Min Range: -0.6405

Max Act: 0.4631. Min Act: -0.0000

Data Index: 271367 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 0.6405. Min Range: -0.6405

Max Act: 0.4634. Min Act: -0.0000

Data Index: 434315 (C4 (Web Text))

Max Activating Token Index: 574

Text #14

Max Range: 0.6405. Min Range: -0.6405

Max Act: 0.4752. Min Act: -0.0000

Data Index: 1250292 (C4 (Web Text))

Max Activating Token Index: 589

Text #15

Max Range: 0.6405. Min Range: -0.6405

Max Act: 0.4631. Min Act: -0.0000

Data Index: 975449 (C4 (Web Text))

Max Activating Token Index: 421

Text #16

Max Range: 0.6405. Min Range: -0.6405

Max Act: 0.4584. Min Act: -0.0000

Data Index: 711817 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 0.6405. Min Range: -0.6405

Max Act: 0.4446. Min Act: -0.0000

Data Index: 895341 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 0.6405. Min Range: -0.6405

Max Act: 0.4675. Min Act: -0.0000

Data Index: 236942 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 0.6405. Min Range: -0.6405

Max Act: 0.4289. Min Act: -0.0000

Data Index: 304553 (C4 (Web Text))

Max Activating Token Index: 847