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

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

Neuron 3693 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0340. Min Act: -0.0002

Data Index: 592714 (C4 (Web Text))

Max Activating Token Index: 562

Text #1

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0330. Min Act: -0.0002

Data Index: 1124874 (C4 (Web Text))

Max Activating Token Index: 914

Text #2

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0317. Min Act: -0.0002

Data Index: 1580160 (Python Code)

Max Activating Token Index: 72

Text #3

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0316. Min Act: -0.0002

Data Index: 416760 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0338. Min Act: -0.0002

Data Index: 847054 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0304. Min Act: -0.0002

Data Index: 288591 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0264. Min Act: -0.0002

Data Index: 341207 (C4 (Web Text))

Max Activating Token Index: 744

Text #7

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0298. Min Act: -0.0002

Data Index: 805325 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0291. Min Act: -0.0002

Data Index: 1321788 (C4 (Web Text))

Max Activating Token Index: 857

Text #9

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0290. Min Act: -0.0002

Data Index: 883431 (C4 (Web Text))

Max Activating Token Index: 884

Text #10

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0285. Min Act: -0.0002

Data Index: 403784 (C4 (Web Text))

Max Activating Token Index: 629

Text #11

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0270. Min Act: -0.0002

Data Index: 1299208 (C4 (Web Text))

Max Activating Token Index: 671

Text #12

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0257. Min Act: -0.0002

Data Index: 590942 (C4 (Web Text))

Max Activating Token Index: 722

Text #13

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0282. Min Act: -0.0002

Data Index: 1148213 (C4 (Web Text))

Max Activating Token Index: 321

Text #14

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0249. Min Act: -0.0002

Data Index: 1003383 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0284. Min Act: -0.0002

Data Index: 1208010 (C4 (Web Text))

Max Activating Token Index: 916

Text #16

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0288. Min Act: -0.0002

Data Index: 1549680 (Python Code)

Max Activating Token Index: 377

Text #17

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0277. Min Act: -0.0002

Data Index: 863542 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0258. Min Act: -0.0002

Data Index: 350790 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0275. Min Act: -0.0002

Data Index: 1313754 (C4 (Web Text))

Max Activating Token Index: 539