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

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

Neuron 5088 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0351. Min Act: -0.0002

Data Index: 179488 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0342. Min Act: -0.0002

Data Index: 1484333 (Python Code)

Max Activating Token Index: 11

Text #2

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0339. Min Act: -0.0002

Data Index: 646814 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0325. Min Act: -0.0002

Data Index: 1363259 (Python Code)

Max Activating Token Index: 7

Text #4

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0325. Min Act: -0.0002

Data Index: 1634191 (Python Code)

Max Activating Token Index: 7

Text #5

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0309. Min Act: -0.0002

Data Index: 751691 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0306. Min Act: -0.0003

Data Index: 306595 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0300. Min Act: -0.0002

Data Index: 684912 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0299. Min Act: -0.0002

Data Index: 66262 (C4 (Web Text))

Max Activating Token Index: 7

Text #9

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0297. Min Act: -0.0003

Data Index: 1147067 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0281. Min Act: -0.0003

Data Index: 1294209 (C4 (Web Text))

Max Activating Token Index: 648

Text #11

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0283. Min Act: -0.0002

Data Index: 1311116 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0287. Min Act: -0.0003

Data Index: 1120509 (C4 (Web Text))

Max Activating Token Index: 856

Text #13

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0281. Min Act: -0.0002

Data Index: 180236 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0282. Min Act: -0.0003

Data Index: 7307 (C4 (Web Text))

Max Activating Token Index: 3

Text #15

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0281. Min Act: -0.0003

Data Index: 964419 (C4 (Web Text))

Max Activating Token Index: 3

Text #16

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0279. Min Act: -0.0003

Data Index: 1114134 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0283. Min Act: -0.0003

Data Index: 1278977 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0282. Min Act: -0.0002

Data Index: 1499421 (Python Code)

Max Activating Token Index: 8

Text #19

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0279. Min Act: -0.0003

Data Index: 1007426 (C4 (Web Text))

Max Activating Token Index: 9