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

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

Neuron 3525 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1468. Min Act: -0.0000

Data Index: 1608467 (Python Code)

Max Activating Token Index: 470

Text #1

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1203. Min Act: -0.0000

Data Index: 1639007 (Python Code)

Max Activating Token Index: 118

Text #2

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1136. Min Act: -0.0000

Data Index: 1597888 (Python Code)

Max Activating Token Index: 359

Text #3

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1202. Min Act: -0.0000

Data Index: 1547140 (Python Code)

Max Activating Token Index: 36

Text #4

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0988. Min Act: -0.0000

Data Index: 1593884 (Python Code)

Max Activating Token Index: 329

Text #5

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1179. Min Act: -0.0000

Data Index: 1439516 (Python Code)

Max Activating Token Index: 574

Text #6

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1131. Min Act: -0.0000

Data Index: 1524248 (Python Code)

Max Activating Token Index: 87

Text #7

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1213. Min Act: -0.0000

Data Index: 1465401 (Python Code)

Max Activating Token Index: 496

Text #8

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1265. Min Act: -0.0000

Data Index: 1495411 (Python Code)

Max Activating Token Index: 308

Text #9

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1123. Min Act: -0.0000

Data Index: 1504675 (Python Code)

Max Activating Token Index: 211

Text #10

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1114. Min Act: -0.0000

Data Index: 1565344 (Python Code)

Max Activating Token Index: 392

Text #11

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1015. Min Act: -0.0000

Data Index: 1536830 (Python Code)

Max Activating Token Index: 249

Text #12

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1108. Min Act: -0.0000

Data Index: 1434206 (Python Code)

Max Activating Token Index: 35

Text #13

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1113. Min Act: -0.0000

Data Index: 1475852 (Python Code)

Max Activating Token Index: 479

Text #14

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1113. Min Act: -0.0000

Data Index: 1514204 (Python Code)

Max Activating Token Index: 300

Text #15

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0991. Min Act: -0.0000

Data Index: 1463168 (Python Code)

Max Activating Token Index: 266

Text #16

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0979. Min Act: -0.0000

Data Index: 1469487 (Python Code)

Max Activating Token Index: 431

Text #17

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1053. Min Act: -0.0000

Data Index: 1568607 (Python Code)

Max Activating Token Index: 223

Text #18

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1040. Min Act: -0.0000

Data Index: 1463746 (Python Code)

Max Activating Token Index: 157

Text #19

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1010. Min Act: -0.0000

Data Index: 1377235 (Python Code)

Max Activating Token Index: 708