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

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

Neuron 4346 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1144. Min Act: -0.0003

Data Index: 880480 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1090. Min Act: -0.0003

Data Index: 1313583 (C4 (Web Text))

Max Activating Token Index: 464

Text #2

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1067. Min Act: -0.0002

Data Index: 1270960 (C4 (Web Text))

Max Activating Token Index: 468

Text #3

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1042. Min Act: -0.0002

Data Index: 51768 (C4 (Web Text))

Max Activating Token Index: 434

Text #4

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1007. Min Act: -0.0003

Data Index: 395722 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1008. Min Act: -0.0003

Data Index: 798583 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0989. Min Act: -0.0003

Data Index: 241342 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1015. Min Act: -0.0002

Data Index: 746282 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0973. Min Act: -0.0003

Data Index: 397468 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0964. Min Act: -0.0003

Data Index: 417601 (C4 (Web Text))

Max Activating Token Index: 9

Text #10

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1003. Min Act: -0.0003

Data Index: 967351 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0958. Min Act: -0.0002

Data Index: 207383 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0995. Min Act: -0.0003

Data Index: 462425 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0967. Min Act: -0.0002

Data Index: 451984 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0959. Min Act: -0.0003

Data Index: 513156 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0954. Min Act: -0.0003

Data Index: 387134 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0952. Min Act: -0.0002

Data Index: 933914 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0941. Min Act: -0.0003

Data Index: 1031207 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0924. Min Act: -0.0003

Data Index: 956320 (C4 (Web Text))

Max Activating Token Index: 281

Text #19

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0924. Min Act: -0.0003

Data Index: 344769 (C4 (Web Text))

Max Activating Token Index: 796