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

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

Neuron 2646 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: 1.4176. Min Range: -1.4176

Max Act: 1.4040. Min Act: -0.0000

Data Index: 1579381 (Python Code)

Max Activating Token Index: 89

Text #1

Max Range: 1.4176. Min Range: -1.4176

Max Act: 1.4176. Min Act: -0.0001

Data Index: 1402591 (Python Code)

Max Activating Token Index: 595

Text #2

Max Range: 1.4176. Min Range: -1.4176

Max Act: 1.3189. Min Act: -0.0001

Data Index: 1556905 (Python Code)

Max Activating Token Index: 468

Text #3

Max Range: 1.4176. Min Range: -1.4176

Max Act: 1.3111. Min Act: -0.0001

Data Index: 1556071 (Python Code)

Max Activating Token Index: 314

Text #4

Max Range: 1.4176. Min Range: -1.4176

Max Act: 1.3316. Min Act: -0.0001

Data Index: 1437703 (Python Code)

Max Activating Token Index: 358

Text #5

Max Range: 1.4176. Min Range: -1.4176

Max Act: 1.1791. Min Act: -0.0001

Data Index: 1395671 (Python Code)

Max Activating Token Index: 671

Text #6

Max Range: 1.4176. Min Range: -1.4176

Max Act: 1.3205. Min Act: -0.0001

Data Index: 1540702 (Python Code)

Max Activating Token Index: 689

Text #7

Max Range: 1.4176. Min Range: -1.4176

Max Act: 1.2573. Min Act: -0.0001

Data Index: 1483354 (Python Code)

Max Activating Token Index: 495

Text #8

Max Range: 1.4176. Min Range: -1.4176

Max Act: 1.1952. Min Act: -0.0001

Data Index: 1438012 (Python Code)

Max Activating Token Index: 432

Text #9

Max Range: 1.4176. Min Range: -1.4176

Max Act: 1.2306. Min Act: -0.0001

Data Index: 1519783 (Python Code)

Max Activating Token Index: 698

Text #10

Max Range: 1.4176. Min Range: -1.4176

Max Act: 1.2952. Min Act: -0.0001

Data Index: 1609952 (Python Code)

Max Activating Token Index: 13

Text #11

Max Range: 1.4176. Min Range: -1.4176

Max Act: 1.2122. Min Act: -0.0000

Data Index: 1502181 (Python Code)

Max Activating Token Index: 19

Text #12

Max Range: 1.4176. Min Range: -1.4176

Max Act: 1.2193. Min Act: -0.0001

Data Index: 1475271 (Python Code)

Max Activating Token Index: 658

Text #13

Max Range: 1.4176. Min Range: -1.4176

Max Act: 1.2217. Min Act: -0.0001

Data Index: 1655014 (Python Code)

Max Activating Token Index: 365

Text #14

Max Range: 1.4176. Min Range: -1.4176

Max Act: 1.1525. Min Act: -0.0001

Data Index: 1575589 (Python Code)

Max Activating Token Index: 990

Text #15

Max Range: 1.4176. Min Range: -1.4176

Max Act: 1.1380. Min Act: -0.0001

Data Index: 1557682 (Python Code)

Max Activating Token Index: 590

Text #16

Max Range: 1.4176. Min Range: -1.4176

Max Act: 1.1946. Min Act: -0.0001

Data Index: 1556231 (Python Code)

Max Activating Token Index: 587

Text #17

Max Range: 1.4176. Min Range: -1.4176

Max Act: 1.1899. Min Act: -0.0000

Data Index: 1437405 (Python Code)

Max Activating Token Index: 15

Text #18

Max Range: 1.4176. Min Range: -1.4176

Max Act: 1.1094. Min Act: -0.0000

Data Index: 1628446 (Python Code)

Max Activating Token Index: 491

Text #19

Max Range: 1.4176. Min Range: -1.4176

Max Act: 1.1067. Min Act: -0.0001

Data Index: 1556351 (Python Code)

Max Activating Token Index: 169