Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3400 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0350. Min Act: -0.0002

Data Index: 116074 (C4 (Web Text))

Max Activating Token Index: 3

Text #1

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0349. Min Act: -0.0002

Data Index: 1134203 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0346. Min Act: -0.0002

Data Index: 800911 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0335. Min Act: -0.0002

Data Index: 1205384 (C4 (Web Text))

Max Activating Token Index: 11

Text #4

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0330. Min Act: -0.0002

Data Index: 946581 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0329. Min Act: -0.0002

Data Index: 884332 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0336. Min Act: -0.0002

Data Index: 865007 (C4 (Web Text))

Max Activating Token Index: 808

Text #7

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0328. Min Act: -0.0002

Data Index: 657659 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0326. Min Act: -0.0002

Data Index: 323930 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0325. Min Act: -0.0002

Data Index: 1194451 (C4 (Web Text))

Max Activating Token Index: 3

Text #10

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0319. Min Act: -0.0002

Data Index: 1065982 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0325. Min Act: -0.0002

Data Index: 134247 (C4 (Web Text))

Max Activating Token Index: 9

Text #12

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0325. Min Act: -0.0002

Data Index: 635388 (C4 (Web Text))

Max Activating Token Index: 9

Text #13

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0324. Min Act: -0.0002

Data Index: 1304269 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0323. Min Act: -0.0002

Data Index: 1336739 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0320. Min Act: -0.0002

Data Index: 1185198 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0326. Min Act: -0.0002

Data Index: 666771 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0313. Min Act: -0.0002

Data Index: 302755 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0313. Min Act: -0.0002

Data Index: 155770 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0317. Min Act: -0.0002

Data Index: 143109 (C4 (Web Text))

Max Activating Token Index: 15