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

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

Neuron 1416 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.7615. Min Act: -0.0001

Data Index: 1146883 (C4 (Web Text))

Max Activating Token Index: 570

Text #1

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.6843. Min Act: -0.0001

Data Index: 1078268 (C4 (Web Text))

Max Activating Token Index: 471

Text #2

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.4113. Min Act: -0.0001

Data Index: 1254177 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.4195. Min Act: -0.0001

Data Index: 126468 (C4 (Web Text))

Max Activating Token Index: 376

Text #4

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.3624. Min Act: -0.0001

Data Index: 386859 (C4 (Web Text))

Max Activating Token Index: 784

Text #5

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.3328. Min Act: -0.0001

Data Index: 338475 (C4 (Web Text))

Max Activating Token Index: 717

Text #6

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.2935. Min Act: -0.0001

Data Index: 1133707 (C4 (Web Text))

Max Activating Token Index: 669

Text #7

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.3623. Min Act: -0.0001

Data Index: 152209 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.3113. Min Act: -0.0001

Data Index: 105555 (C4 (Web Text))

Max Activating Token Index: 308

Text #9

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.1837. Min Act: -0.0001

Data Index: 1151664 (C4 (Web Text))

Max Activating Token Index: 905

Text #10

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.2633. Min Act: -0.0001

Data Index: 865432 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.2195. Min Act: -0.0001

Data Index: 41253 (C4 (Web Text))

Max Activating Token Index: 548

Text #12

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.1971. Min Act: -0.0001

Data Index: 715580 (C4 (Web Text))

Max Activating Token Index: 462

Text #13

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.2592. Min Act: -0.0001

Data Index: 1088650 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.1815. Min Act: -0.0001

Data Index: 767329 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.1014. Min Act: -0.0001

Data Index: 956988 (C4 (Web Text))

Max Activating Token Index: 840

Text #16

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.2783. Min Act: -0.0001

Data Index: 294232 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.2545. Min Act: -0.0001

Data Index: 133724 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.2560. Min Act: -0.0001

Data Index: 1081437 (C4 (Web Text))

Max Activating Token Index: 576

Text #19

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.1672. Min Act: -0.0001

Data Index: 54915 (C4 (Web Text))

Max Activating Token Index: 193