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

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

Neuron 1896 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0595. Min Act: -0.0001

Data Index: 289515 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0569. Min Act: -0.0002

Data Index: 706882 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0570. Min Act: -0.0001

Data Index: 668637 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0527. Min Act: -0.0001

Data Index: 1233867 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0527. Min Act: -0.0002

Data Index: 349237 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0544. Min Act: -0.0001

Data Index: 1015961 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0554. Min Act: -0.0001

Data Index: 1222282 (C4 (Web Text))

Max Activating Token Index: 4

Text #7

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0554. Min Act: -0.0001

Data Index: 1030307 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0535. Min Act: -0.0002

Data Index: 224057 (C4 (Web Text))

Max Activating Token Index: 17

Text #9

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0518. Min Act: -0.0001

Data Index: 936516 (C4 (Web Text))

Max Activating Token Index: 9

Text #10

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0517. Min Act: -0.0001

Data Index: 208190 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0514. Min Act: -0.0001

Data Index: 398639 (C4 (Web Text))

Max Activating Token Index: 274

Text #12

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0549. Min Act: -0.0001

Data Index: 1256819 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0500. Min Act: -0.0001

Data Index: 1293213 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0534. Min Act: -0.0001

Data Index: 1347841 (C4 (Web Text))

Max Activating Token Index: 11

Text #15

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0529. Min Act: -0.0001

Data Index: 864509 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0524. Min Act: -0.0001

Data Index: 1285726 (C4 (Web Text))

Max Activating Token Index: 9

Text #17

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0519. Min Act: -0.0001

Data Index: 1253849 (C4 (Web Text))

Max Activating Token Index: 17

Text #18

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0497. Min Act: -0.0001

Data Index: 1195043 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0492. Min Act: -0.0001

Data Index: 158509 (C4 (Web Text))

Max Activating Token Index: 8