Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3347 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.5955. Min Act: -0.0000

Data Index: 727179 (C4 (Web Text))

Max Activating Token Index: 448

Text #1

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.5266. Min Act: -0.0000

Data Index: 1016740 (C4 (Web Text))

Max Activating Token Index: 324

Text #2

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.5291. Min Act: -0.0000

Data Index: 1353886 (C4 (Web Text))

Max Activating Token Index: 601

Text #3

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.4828. Min Act: -0.0000

Data Index: 1277032 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.4645. Min Act: -0.0000

Data Index: 577880 (C4 (Web Text))

Max Activating Token Index: 437

Text #5

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.4923. Min Act: -0.0000

Data Index: 637621 (C4 (Web Text))

Max Activating Token Index: 502

Text #6

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.4571. Min Act: -0.0000

Data Index: 209269 (C4 (Web Text))

Max Activating Token Index: 988

Text #7

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.4235. Min Act: -0.0000

Data Index: 1149931 (C4 (Web Text))

Max Activating Token Index: 462

Text #8

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.4375. Min Act: -0.0000

Data Index: 1205779 (C4 (Web Text))

Max Activating Token Index: 723

Text #9

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.4465. Min Act: -0.0000

Data Index: 224475 (C4 (Web Text))

Max Activating Token Index: 976

Text #10

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.4293. Min Act: -0.0000

Data Index: 120905 (C4 (Web Text))

Max Activating Token Index: 34

Text #11

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.4352. Min Act: -0.0000

Data Index: 539534 (C4 (Web Text))

Max Activating Token Index: 531

Text #12

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.4183. Min Act: -0.0000

Data Index: 1030939 (C4 (Web Text))

Max Activating Token Index: 866

Text #13

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.4179. Min Act: -0.0000

Data Index: 990554 (C4 (Web Text))

Max Activating Token Index: 307

Text #14

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.4187. Min Act: -0.0000

Data Index: 310365 (C4 (Web Text))

Max Activating Token Index: 112

Text #15

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.4271. Min Act: -0.0000

Data Index: 172156 (C4 (Web Text))

Max Activating Token Index: 973

Text #16

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.4199. Min Act: -0.0000

Data Index: 318085 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.4042. Min Act: 0.0000

Data Index: 982998 (C4 (Web Text))

Max Activating Token Index: 77

Text #18

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.4164. Min Act: -0.0000

Data Index: 150579 (C4 (Web Text))

Max Activating Token Index: 384

Text #19

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.4332. Min Act: -0.0000

Data Index: 735961 (C4 (Web Text))

Max Activating Token Index: 51