Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2647 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.6436. Min Act: -0.0002

Data Index: 1016266 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.6380. Min Act: -0.0002

Data Index: 634758 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5781. Min Act: -0.0002

Data Index: 489762 (C4 (Web Text))

Max Activating Token Index: 8

Text #3

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5588. Min Act: -0.0003

Data Index: 49418 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5494. Min Act: -0.0002

Data Index: 369140 (C4 (Web Text))

Max Activating Token Index: 7

Text #5

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5727. Min Act: -0.0002

Data Index: 828266 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5860. Min Act: -0.0003

Data Index: 615180 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5209. Min Act: -0.0003

Data Index: 591640 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5379. Min Act: -0.0002

Data Index: 1040628 (C4 (Web Text))

Max Activating Token Index: 7

Text #9

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5280. Min Act: -0.0003

Data Index: 964524 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5427. Min Act: -0.0003

Data Index: 406700 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5168. Min Act: -0.0003

Data Index: 144011 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5062. Min Act: -0.0003

Data Index: 1302983 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5060. Min Act: -0.0002

Data Index: 226730 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5043. Min Act: -0.0002

Data Index: 1331729 (C4 (Web Text))

Max Activating Token Index: 8

Text #15

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5055. Min Act: -0.0003

Data Index: 1194454 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.4815. Min Act: -0.0002

Data Index: 490259 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.4925. Min Act: -0.0002

Data Index: 1245801 (C4 (Web Text))

Max Activating Token Index: 6

Text #18

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.4875. Min Act: -0.0002

Data Index: 652120 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.4671. Min Act: -0.0003

Data Index: 321344 (C4 (Web Text))

Max Activating Token Index: 37