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

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

Neuron 3334 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1774. Min Act: -0.0001

Data Index: 1424875 (Python Code)

Max Activating Token Index: 10

Text #1

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1769. Min Act: -0.0001

Data Index: 1424374 (Python Code)

Max Activating Token Index: 1000

Text #2

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1510. Min Act: -0.0001

Data Index: 131713 (C4 (Web Text))

Max Activating Token Index: 609

Text #3

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1419. Min Act: -0.0001

Data Index: 1440361 (Python Code)

Max Activating Token Index: 790

Text #4

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1402. Min Act: -0.0001

Data Index: 1491507 (Python Code)

Max Activating Token Index: 985

Text #5

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1354. Min Act: -0.0001

Data Index: 1384328 (Python Code)

Max Activating Token Index: 10

Text #6

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1348. Min Act: -0.0001

Data Index: 1526057 (Python Code)

Max Activating Token Index: 584

Text #7

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1344. Min Act: -0.0001

Data Index: 1238022 (C4 (Web Text))

Max Activating Token Index: 741

Text #8

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1323. Min Act: -0.0001

Data Index: 1468627 (Python Code)

Max Activating Token Index: 151

Text #9

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1353. Min Act: -0.0001

Data Index: 994062 (C4 (Web Text))

Max Activating Token Index: 531

Text #10

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1247. Min Act: -0.0001

Data Index: 845308 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1288. Min Act: -0.0001

Data Index: 880911 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1324. Min Act: -0.0001

Data Index: 827178 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1272. Min Act: -0.0001

Data Index: 1479061 (Python Code)

Max Activating Token Index: 71

Text #14

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1266. Min Act: -0.0001

Data Index: 1621900 (Python Code)

Max Activating Token Index: 175

Text #15

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1219. Min Act: -0.0001

Data Index: 1433011 (Python Code)

Max Activating Token Index: 20

Text #16

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1213. Min Act: -0.0001

Data Index: 1532439 (Python Code)

Max Activating Token Index: 576

Text #17

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1293. Min Act: -0.0001

Data Index: 1481946 (Python Code)

Max Activating Token Index: 4

Text #18

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1245. Min Act: -0.0001

Data Index: 1357738 (C4 (Web Text))

Max Activating Token Index: 266

Text #19

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1238. Min Act: -0.0001

Data Index: 1517267 (Python Code)

Max Activating Token Index: 446