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

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

Neuron 3990 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1938. Min Act: -0.0001

Data Index: 310193 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1931. Min Act: -0.0001

Data Index: 131973 (C4 (Web Text))

Max Activating Token Index: 867

Text #2

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1853. Min Act: -0.0001

Data Index: 1175844 (C4 (Web Text))

Max Activating Token Index: 989

Text #3

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.2067. Min Act: -0.0001

Data Index: 834405 (C4 (Web Text))

Max Activating Token Index: 498

Text #4

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1757. Min Act: -0.0001

Data Index: 220458 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1864. Min Act: -0.0001

Data Index: 1148098 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1970. Min Act: -0.0000

Data Index: 492578 (C4 (Web Text))

Max Activating Token Index: 1011

Text #7

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1723. Min Act: -0.0001

Data Index: 355127 (C4 (Web Text))

Max Activating Token Index: 285

Text #8

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1747. Min Act: -0.0000

Data Index: 309228 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1844. Min Act: -0.0001

Data Index: 1178709 (C4 (Web Text))

Max Activating Token Index: 847

Text #10

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1691. Min Act: -0.0001

Data Index: 1055480 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1918. Min Act: -0.0001

Data Index: 876049 (C4 (Web Text))

Max Activating Token Index: 405

Text #12

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1693. Min Act: -0.0001

Data Index: 509688 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1736. Min Act: -0.0001

Data Index: 718518 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1617. Min Act: -0.0001

Data Index: 713383 (C4 (Web Text))

Max Activating Token Index: 571

Text #15

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1607. Min Act: -0.0001

Data Index: 551076 (C4 (Web Text))

Max Activating Token Index: 832

Text #16

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1547. Min Act: -0.0001

Data Index: 168740 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1641. Min Act: -0.0001

Data Index: 250911 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1872. Min Act: -0.0000

Data Index: 139659 (C4 (Web Text))

Max Activating Token Index: 548

Text #19

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1648. Min Act: -0.0001

Data Index: 907907 (C4 (Web Text))

Max Activating Token Index: 655