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

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

Neuron 3098 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0345. Min Act: -0.0002

Data Index: 87673 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0328. Min Act: -0.0002

Data Index: 1316105 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0309. Min Act: -0.0002

Data Index: 98845 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0309. Min Act: -0.0002

Data Index: 309373 (C4 (Web Text))

Max Activating Token Index: 18

Text #4

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0299. Min Act: -0.0002

Data Index: 446898 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0292. Min Act: -0.0002

Data Index: 927129 (C4 (Web Text))

Max Activating Token Index: 17

Text #6

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0287. Min Act: -0.0002

Data Index: 868456 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0286. Min Act: -0.0002

Data Index: 567691 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0281. Min Act: -0.0002

Data Index: 217415 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0275. Min Act: -0.0002

Data Index: 927976 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0277. Min Act: -0.0002

Data Index: 21855 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0275. Min Act: -0.0002

Data Index: 435076 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0273. Min Act: -0.0002

Data Index: 721150 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0267. Min Act: -0.0002

Data Index: 1138527 (C4 (Web Text))

Max Activating Token Index: 13

Text #14

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0269. Min Act: -0.0002

Data Index: 433184 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0271. Min Act: -0.0002

Data Index: 683285 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0266. Min Act: -0.0002

Data Index: 1224187 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0265. Min Act: -0.0002

Data Index: 301995 (C4 (Web Text))

Max Activating Token Index: 6

Text #18

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0260. Min Act: -0.0002

Data Index: 720439 (C4 (Web Text))

Max Activating Token Index: 4

Text #19

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0258. Min Act: -0.0003

Data Index: 824434 (C4 (Web Text))

Max Activating Token Index: 10