Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1839 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0467. Min Act: -0.0001

Data Index: 1362201 (Python Code)

Max Activating Token Index: 230

Text #1

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0339. Min Act: -0.0001

Data Index: 1364588 (Python Code)

Max Activating Token Index: 73

Text #2

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0326. Min Act: -0.0001

Data Index: 1481835 (Python Code)

Max Activating Token Index: 234

Text #3

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0316. Min Act: -0.0001

Data Index: 1570819 (Python Code)

Max Activating Token Index: 614

Text #4

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0297. Min Act: -0.0000

Data Index: 1535556 (Python Code)

Max Activating Token Index: 453

Text #5

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0298. Min Act: -0.0001

Data Index: 1404467 (Python Code)

Max Activating Token Index: 63

Text #6

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0307. Min Act: -0.0001

Data Index: 527551 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0277. Min Act: -0.0001

Data Index: 1597812 (Python Code)

Max Activating Token Index: 257

Text #8

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0261. Min Act: -0.0001

Data Index: 1574744 (Python Code)

Max Activating Token Index: 844

Text #9

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0265. Min Act: -0.0001

Data Index: 1486931 (Python Code)

Max Activating Token Index: 274

Text #10

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0268. Min Act: -0.0001

Data Index: 1420335 (Python Code)

Max Activating Token Index: 1001

Text #11

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0262. Min Act: -0.0001

Data Index: 1389435 (Python Code)

Max Activating Token Index: 328

Text #12

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0266. Min Act: -0.0001

Data Index: 1619740 (Python Code)

Max Activating Token Index: 451

Text #13

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0277. Min Act: -0.0001

Data Index: 1583398 (Python Code)

Max Activating Token Index: 385

Text #14

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0270. Min Act: -0.0001

Data Index: 1423263 (Python Code)

Max Activating Token Index: 33

Text #15

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0254. Min Act: -0.0001

Data Index: 1598717 (Python Code)

Max Activating Token Index: 608

Text #16

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0259. Min Act: -0.0000

Data Index: 1619988 (Python Code)

Max Activating Token Index: 145

Text #17

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0234. Min Act: -0.0001

Data Index: 1396518 (Python Code)

Max Activating Token Index: 710

Text #18

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0259. Min Act: -0.0001

Data Index: 1569951 (Python Code)

Max Activating Token Index: 846

Text #19

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0246. Min Act: -0.0001

Data Index: 1648450 (Python Code)

Max Activating Token Index: 662