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

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

Neuron 840 in Layer 0

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: 0.0377. Min Range: -0.0377

Max Act: 0.0377. Min Act: -0.0001

Data Index: 34304 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0355. Min Act: -0.0001

Data Index: 1601585 (Python Code)

Max Activating Token Index: 10

Text #2

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0318. Min Act: -0.0001

Data Index: 565714 (C4 (Web Text))

Max Activating Token Index: 627

Text #3

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0309. Min Act: -0.0001

Data Index: 1359836 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0292. Min Act: -0.0001

Data Index: 830677 (C4 (Web Text))

Max Activating Token Index: 196

Text #5

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0296. Min Act: -0.0001

Data Index: 1319949 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0283. Min Act: -0.0001

Data Index: 60900 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0281. Min Act: -0.0001

Data Index: 1284835 (C4 (Web Text))

Max Activating Token Index: 581

Text #8

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0278. Min Act: -0.0001

Data Index: 1354112 (C4 (Web Text))

Max Activating Token Index: 83

Text #9

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0269. Min Act: -0.0001

Data Index: 347410 (C4 (Web Text))

Max Activating Token Index: 312

Text #10

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0265. Min Act: -0.0002

Data Index: 797328 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0270. Min Act: -0.0001

Data Index: 994292 (C4 (Web Text))

Max Activating Token Index: 985

Text #12

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0266. Min Act: -0.0001

Data Index: 666816 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0263. Min Act: -0.0001

Data Index: 1548755 (Python Code)

Max Activating Token Index: 331

Text #14

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0260. Min Act: -0.0001

Data Index: 855441 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0259. Min Act: -0.0001

Data Index: 207530 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0260. Min Act: -0.0001

Data Index: 478019 (C4 (Web Text))

Max Activating Token Index: 472

Text #17

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0264. Min Act: -0.0001

Data Index: 281945 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0254. Min Act: -0.0001

Data Index: 1027130 (C4 (Web Text))

Max Activating Token Index: 99

Text #19

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0256. Min Act: -0.0001

Data Index: 337487 (C4 (Web Text))

Max Activating Token Index: 26