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

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

Neuron 4066 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9771. Min Range: -0.9771

Max Act: 0.9771. Min Act: -0.0000

Data Index: 88605 (C4 (Web Text))

Max Activating Token Index: 362

Text #1

Max Range: 0.9771. Min Range: -0.9771

Max Act: 0.7246. Min Act: -0.0000

Data Index: 1235559 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 0.9771. Min Range: -0.9771

Max Act: 0.6986. Min Act: -0.0000

Data Index: 994489 (C4 (Web Text))

Max Activating Token Index: 477

Text #3

Max Range: 0.9771. Min Range: -0.9771

Max Act: 0.6951. Min Act: -0.0000

Data Index: 48862 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 0.9771. Min Range: -0.9771

Max Act: 0.5790. Min Act: -0.0000

Data Index: 1218864 (C4 (Web Text))

Max Activating Token Index: 628

Text #5

Max Range: 0.9771. Min Range: -0.9771

Max Act: 0.6001. Min Act: -0.0000

Data Index: 38439 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 0.9771. Min Range: -0.9771

Max Act: 0.5973. Min Act: -0.0000

Data Index: 613012 (C4 (Web Text))

Max Activating Token Index: 227

Text #7

Max Range: 0.9771. Min Range: -0.9771

Max Act: 0.6129. Min Act: -0.0000

Data Index: 1055741 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 0.9771. Min Range: -0.9771

Max Act: 0.6231. Min Act: -0.0000

Data Index: 176163 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 0.9771. Min Range: -0.9771

Max Act: 0.5983. Min Act: -0.0000

Data Index: 353521 (C4 (Web Text))

Max Activating Token Index: 741

Text #10

Max Range: 0.9771. Min Range: -0.9771

Max Act: 0.6060. Min Act: -0.0000

Data Index: 360193 (C4 (Web Text))

Max Activating Token Index: 405

Text #11

Max Range: 0.9771. Min Range: -0.9771

Max Act: 0.6208. Min Act: -0.0000

Data Index: 1109998 (C4 (Web Text))

Max Activating Token Index: 971

Text #12

Max Range: 0.9771. Min Range: -0.9771

Max Act: 0.5503. Min Act: -0.0000

Data Index: 523849 (C4 (Web Text))

Max Activating Token Index: 595

Text #13

Max Range: 0.9771. Min Range: -0.9771

Max Act: 0.6207. Min Act: -0.0000

Data Index: 151652 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 0.9771. Min Range: -0.9771

Max Act: 0.5844. Min Act: -0.0000

Data Index: 1214358 (C4 (Web Text))

Max Activating Token Index: 582

Text #15

Max Range: 0.9771. Min Range: -0.9771

Max Act: 0.5948. Min Act: -0.0000

Data Index: 848216 (C4 (Web Text))

Max Activating Token Index: 741

Text #16

Max Range: 0.9771. Min Range: -0.9771

Max Act: 0.5669. Min Act: -0.0000

Data Index: 688427 (C4 (Web Text))

Max Activating Token Index: 361

Text #17

Max Range: 0.9771. Min Range: -0.9771

Max Act: 0.6808. Min Act: -0.0000

Data Index: 489569 (C4 (Web Text))

Max Activating Token Index: 860

Text #18

Max Range: 0.9771. Min Range: -0.9771

Max Act: 0.5884. Min Act: -0.0000

Data Index: 591441 (C4 (Web Text))

Max Activating Token Index: 986

Text #19

Max Range: 0.9771. Min Range: -0.9771

Max Act: 0.5621. Min Act: -0.0000

Data Index: 72787 (C4 (Web Text))

Max Activating Token Index: 876