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

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

Neuron 1315 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2170. Min Range: -5.2170

Max Act: 5.2170. Min Act: -0.0000

Data Index: 846787 (C4 (Web Text))

Max Activating Token Index: 425

Text #1

Max Range: 5.2170. Min Range: -5.2170

Max Act: 3.4629. Min Act: -0.0000

Data Index: 655983 (C4 (Web Text))

Max Activating Token Index: 1012

Text #2

Max Range: 5.2170. Min Range: -5.2170

Max Act: 3.2398. Min Act: -0.0000

Data Index: 118914 (C4 (Web Text))

Max Activating Token Index: 843

Text #3

Max Range: 5.2170. Min Range: -5.2170

Max Act: 3.4204. Min Act: -0.0000

Data Index: 1089928 (C4 (Web Text))

Max Activating Token Index: 8

Text #4

Max Range: 5.2170. Min Range: -5.2170

Max Act: 3.2549. Min Act: -0.0000

Data Index: 430538 (C4 (Web Text))

Max Activating Token Index: 884

Text #5

Max Range: 5.2170. Min Range: -5.2170

Max Act: 3.1578. Min Act: -0.0000

Data Index: 338965 (C4 (Web Text))

Max Activating Token Index: 852

Text #6

Max Range: 5.2170. Min Range: -5.2170

Max Act: 2.9483. Min Act: -0.0000

Data Index: 1150005 (C4 (Web Text))

Max Activating Token Index: 413

Text #7

Max Range: 5.2170. Min Range: -5.2170

Max Act: 2.9522. Min Act: -0.0000

Data Index: 915891 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 5.2170. Min Range: -5.2170

Max Act: 3.0626. Min Act: -0.0000

Data Index: 979046 (C4 (Web Text))

Max Activating Token Index: 794

Text #9

Max Range: 5.2170. Min Range: -5.2170

Max Act: 2.7440. Min Act: -0.0000

Data Index: 493276 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 5.2170. Min Range: -5.2170

Max Act: 2.7895. Min Act: -0.0000

Data Index: 363206 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 5.2170. Min Range: -5.2170

Max Act: 2.7624. Min Act: -0.0000

Data Index: 1286620 (C4 (Web Text))

Max Activating Token Index: 683

Text #12

Max Range: 5.2170. Min Range: -5.2170

Max Act: 2.7478. Min Act: -0.0000

Data Index: 331514 (C4 (Web Text))

Max Activating Token Index: 190

Text #13

Max Range: 5.2170. Min Range: -5.2170

Max Act: 2.7561. Min Act: -0.0000

Data Index: 160809 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 5.2170. Min Range: -5.2170

Max Act: 2.6489. Min Act: -0.0000

Data Index: 1327832 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 5.2170. Min Range: -5.2170

Max Act: 2.6227. Min Act: -0.0000

Data Index: 1293742 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 5.2170. Min Range: -5.2170

Max Act: 2.5604. Min Act: -0.0000

Data Index: 304533 (C4 (Web Text))

Max Activating Token Index: 774

Text #17

Max Range: 5.2170. Min Range: -5.2170

Max Act: 2.4212. Min Act: -0.0000

Data Index: 873629 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 5.2170. Min Range: -5.2170

Max Act: 2.5350. Min Act: -0.0000

Data Index: 745304 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 5.2170. Min Range: -5.2170

Max Act: 2.5351. Min Act: -0.0000

Data Index: 428295 (C4 (Web Text))

Max Activating Token Index: 315