Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3409 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6969. Min Range: -1.6969

Max Act: 1.6969. Min Act: 0.0000

Data Index: 1413069 (Python Code)

Max Activating Token Index: 654

Text #1

Max Range: 1.6969. Min Range: -1.6969

Max Act: 1.4792. Min Act: 0.0001

Data Index: 1431226 (Python Code)

Max Activating Token Index: 965

Text #2

Max Range: 1.6969. Min Range: -1.6969

Max Act: 1.5830. Min Act: 0.0001

Data Index: 1392075 (Python Code)

Max Activating Token Index: 700

Text #3

Max Range: 1.6969. Min Range: -1.6969

Max Act: 1.3523. Min Act: 0.0000

Data Index: 1555243 (Python Code)

Max Activating Token Index: 80

Text #4

Max Range: 1.6969. Min Range: -1.6969

Max Act: 1.1949. Min Act: -0.0000

Data Index: 1443660 (Python Code)

Max Activating Token Index: 60

Text #5

Max Range: 1.6969. Min Range: -1.6969

Max Act: 1.1525. Min Act: -0.0000

Data Index: 1606265 (Python Code)

Max Activating Token Index: 201

Text #6

Max Range: 1.6969. Min Range: -1.6969

Max Act: 1.3296. Min Act: 0.0000

Data Index: 1462555 (Python Code)

Max Activating Token Index: 107

Text #7

Max Range: 1.6969. Min Range: -1.6969

Max Act: 1.2987. Min Act: 0.0001

Data Index: 1648249 (Python Code)

Max Activating Token Index: 35

Text #8

Max Range: 1.6969. Min Range: -1.6969

Max Act: 1.2993. Min Act: -0.0000

Data Index: 1418193 (Python Code)

Max Activating Token Index: 521

Text #9

Max Range: 1.6969. Min Range: -1.6969

Max Act: 1.2533. Min Act: -0.0001

Data Index: 1448446 (Python Code)

Max Activating Token Index: 584

Text #10

Max Range: 1.6969. Min Range: -1.6969

Max Act: 1.3148. Min Act: -0.0000

Data Index: 1536818 (Python Code)

Max Activating Token Index: 623

Text #11

Max Range: 1.6969. Min Range: -1.6969

Max Act: 1.1292. Min Act: -0.0000

Data Index: 1472555 (Python Code)

Max Activating Token Index: 384

Text #12

Max Range: 1.6969. Min Range: -1.6969

Max Act: 1.1892. Min Act: -0.0000

Data Index: 1484008 (Python Code)

Max Activating Token Index: 61

Text #13

Max Range: 1.6969. Min Range: -1.6969

Max Act: 1.0693. Min Act: -0.0000

Data Index: 1419832 (Python Code)

Max Activating Token Index: 184

Text #14

Max Range: 1.6969. Min Range: -1.6969

Max Act: 1.1402. Min Act: -0.0000

Data Index: 1612845 (Python Code)

Max Activating Token Index: 356

Text #15

Max Range: 1.6969. Min Range: -1.6969

Max Act: 1.0711. Min Act: -0.0001

Data Index: 1381826 (Python Code)

Max Activating Token Index: 828

Text #16

Max Range: 1.6969. Min Range: -1.6969

Max Act: 1.1571. Min Act: -0.0000

Data Index: 1588016 (Python Code)

Max Activating Token Index: 189

Text #17

Max Range: 1.6969. Min Range: -1.6969

Max Act: 1.1176. Min Act: -0.0000

Data Index: 1464037 (Python Code)

Max Activating Token Index: 357

Text #18

Max Range: 1.6969. Min Range: -1.6969

Max Act: 1.0410. Min Act: -0.0000

Data Index: 1451574 (Python Code)

Max Activating Token Index: 724

Text #19

Max Range: 1.6969. Min Range: -1.6969

Max Act: 1.0107. Min Act: -0.0000

Data Index: 1371998 (Python Code)

Max Activating Token Index: 886