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

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

Neuron 4381 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8648. Min Range: -2.8648

Max Act: 2.8648. Min Act: -0.0000

Data Index: 462127 (C4 (Web Text))

Max Activating Token Index: 235

Text #1

Max Range: 2.8648. Min Range: -2.8648

Max Act: 2.7543. Min Act: -0.0000

Data Index: 1240097 (C4 (Web Text))

Max Activating Token Index: 126

Text #2

Max Range: 2.8648. Min Range: -2.8648

Max Act: 2.7689. Min Act: -0.0000

Data Index: 62750 (C4 (Web Text))

Max Activating Token Index: 279

Text #3

Max Range: 2.8648. Min Range: -2.8648

Max Act: 2.5066. Min Act: -0.0000

Data Index: 1187195 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 2.8648. Min Range: -2.8648

Max Act: 2.4270. Min Act: -0.0000

Data Index: 548572 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 2.8648. Min Range: -2.8648

Max Act: 2.4924. Min Act: -0.0000

Data Index: 1272301 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 2.8648. Min Range: -2.8648

Max Act: 2.4589. Min Act: -0.0000

Data Index: 1208694 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 2.8648. Min Range: -2.8648

Max Act: 2.5942. Min Act: -0.0000

Data Index: 1215016 (C4 (Web Text))

Max Activating Token Index: 642

Text #8

Max Range: 2.8648. Min Range: -2.8648

Max Act: 2.3289. Min Act: -0.0000

Data Index: 1047783 (C4 (Web Text))

Max Activating Token Index: 772

Text #9

Max Range: 2.8648. Min Range: -2.8648

Max Act: 2.1860. Min Act: -0.0000

Data Index: 1148959 (C4 (Web Text))

Max Activating Token Index: 558

Text #10

Max Range: 2.8648. Min Range: -2.8648

Max Act: 2.3202. Min Act: -0.0000

Data Index: 160177 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 2.8648. Min Range: -2.8648

Max Act: 2.2438. Min Act: -0.0000

Data Index: 420124 (C4 (Web Text))

Max Activating Token Index: 574

Text #12

Max Range: 2.8648. Min Range: -2.8648

Max Act: 2.3332. Min Act: -0.0000

Data Index: 744613 (C4 (Web Text))

Max Activating Token Index: 895

Text #13

Max Range: 2.8648. Min Range: -2.8648

Max Act: 2.0454. Min Act: -0.0000

Data Index: 1262847 (C4 (Web Text))

Max Activating Token Index: 354

Text #14

Max Range: 2.8648. Min Range: -2.8648

Max Act: 2.0259. Min Act: -0.0000

Data Index: 29209 (C4 (Web Text))

Max Activating Token Index: 667

Text #15

Max Range: 2.8648. Min Range: -2.8648

Max Act: 2.0188. Min Act: -0.0000

Data Index: 9201 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 2.8648. Min Range: -2.8648

Max Act: 2.1333. Min Act: -0.0000

Data Index: 114149 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 2.8648. Min Range: -2.8648

Max Act: 2.2253. Min Act: -0.0000

Data Index: 1310615 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 2.8648. Min Range: -2.8648

Max Act: 2.0647. Min Act: -0.0000

Data Index: 381285 (C4 (Web Text))

Max Activating Token Index: 794

Text #19

Max Range: 2.8648. Min Range: -2.8648

Max Act: 2.0224. Min Act: -0.0000

Data Index: 651803 (C4 (Web Text))

Max Activating Token Index: 599