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

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

Neuron 3837 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: 0.0744. Min Range: -0.0744

Max Act: 0.0437. Min Act: -0.0001

Data Index: 1061008 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0645. Min Act: -0.0001

Data Index: 451129 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0694. Min Act: -0.0001

Data Index: 253373 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0555. Min Act: -0.0001

Data Index: 449716 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0744. Min Act: -0.0001

Data Index: 221059 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0585. Min Act: -0.0001

Data Index: 96731 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0397. Min Act: -0.0001

Data Index: 502152 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0331. Min Act: -0.0001

Data Index: 70397 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0378. Min Act: -0.0001

Data Index: 1464964 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0301. Min Act: -0.0001

Data Index: 352765 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0456. Min Act: -0.0001

Data Index: 655518 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0410. Min Act: -0.0001

Data Index: 615911 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0502. Min Act: -0.0001

Data Index: 818740 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0436. Min Act: -0.0001

Data Index: 1276741 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0515. Min Act: -0.0001

Data Index: 865937 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0341. Min Act: -0.0001

Data Index: 1247123 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0474. Min Act: -0.0001

Data Index: 1608782 (Python Code)

Max Activating Token Index: 895

Text #17

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0415. Min Act: -0.0001

Data Index: 1215699 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0316. Min Act: -0.0001

Data Index: 513236 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0381. Min Act: -0.0001

Data Index: 1110323 (C4 (Web Text))

Max Activating Token Index: 1023