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

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

Neuron 649 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: 1.2405. Min Range: -1.2405

Max Act: 1.0904. Min Act: -0.0001

Data Index: 1246496 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 1.2405. Min Range: -1.2405

Max Act: 0.9900. Min Act: -0.0001

Data Index: 1077914 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 1.2405. Min Range: -1.2405

Max Act: 1.1034. Min Act: -0.0001

Data Index: 286978 (C4 (Web Text))

Max Activating Token Index: 612

Text #3

Max Range: 1.2405. Min Range: -1.2405

Max Act: 0.9868. Min Act: -0.0002

Data Index: 39325 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 1.2405. Min Range: -1.2405

Max Act: 1.0384. Min Act: -0.0002

Data Index: 1137145 (C4 (Web Text))

Max Activating Token Index: 377

Text #5

Max Range: 1.2405. Min Range: -1.2405

Max Act: 1.2405. Min Act: -0.0002

Data Index: 589968 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 1.2405. Min Range: -1.2405

Max Act: 0.8364. Min Act: -0.0001

Data Index: 1273823 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 1.2405. Min Range: -1.2405

Max Act: 0.9351. Min Act: -0.0001

Data Index: 1190024 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 1.2405. Min Range: -1.2405

Max Act: 1.0279. Min Act: -0.0002

Data Index: 815893 (C4 (Web Text))

Max Activating Token Index: 321

Text #9

Max Range: 1.2405. Min Range: -1.2405

Max Act: 1.0591. Min Act: -0.0002

Data Index: 298365 (C4 (Web Text))

Max Activating Token Index: 569

Text #10

Max Range: 1.2405. Min Range: -1.2405

Max Act: 0.8878. Min Act: -0.0002

Data Index: 560726 (C4 (Web Text))

Max Activating Token Index: 953

Text #11

Max Range: 1.2405. Min Range: -1.2405

Max Act: 1.0540. Min Act: -0.0001

Data Index: 67698 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 1.2405. Min Range: -1.2405

Max Act: 0.9893. Min Act: -0.0002

Data Index: 307922 (C4 (Web Text))

Max Activating Token Index: 519

Text #13

Max Range: 1.2405. Min Range: -1.2405

Max Act: 0.9828. Min Act: -0.0002

Data Index: 1195781 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 1.2405. Min Range: -1.2405

Max Act: 0.9710. Min Act: -0.0002

Data Index: 297427 (C4 (Web Text))

Max Activating Token Index: 622

Text #15

Max Range: 1.2405. Min Range: -1.2405

Max Act: 0.9073. Min Act: -0.0002

Data Index: 394422 (C4 (Web Text))

Max Activating Token Index: 874

Text #16

Max Range: 1.2405. Min Range: -1.2405

Max Act: 0.9646. Min Act: -0.0002

Data Index: 276463 (C4 (Web Text))

Max Activating Token Index: 911

Text #17

Max Range: 1.2405. Min Range: -1.2405

Max Act: 0.8937. Min Act: -0.0002

Data Index: 1208384 (C4 (Web Text))

Max Activating Token Index: 595

Text #18

Max Range: 1.2405. Min Range: -1.2405

Max Act: 0.9503. Min Act: -0.0002

Data Index: 284630 (C4 (Web Text))

Max Activating Token Index: 40

Text #19

Max Range: 1.2405. Min Range: -1.2405

Max Act: 0.8751. Min Act: -0.0001

Data Index: 700455 (C4 (Web Text))

Max Activating Token Index: 741