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

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

Neuron 3383 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.3089. Min Act: -0.0000

Data Index: 1595619 (Python Code)

Max Activating Token Index: 15

Text #1

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2666. Min Act: -0.0000

Data Index: 1615827 (Python Code)

Max Activating Token Index: 15

Text #2

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2625. Min Act: -0.0000

Data Index: 1391514 (Python Code)

Max Activating Token Index: 13

Text #3

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2472. Min Act: -0.0000

Data Index: 1596976 (Python Code)

Max Activating Token Index: 19

Text #4

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2506. Min Act: -0.0000

Data Index: 1490120 (Python Code)

Max Activating Token Index: 38

Text #5

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2202. Min Act: -0.0000

Data Index: 1540224 (Python Code)

Max Activating Token Index: 27

Text #6

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2680. Min Act: -0.0000

Data Index: 812800 (C4 (Web Text))

Max Activating Token Index: 358

Text #7

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2410. Min Act: -0.0000

Data Index: 1365700 (Python Code)

Max Activating Token Index: 15

Text #8

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2163. Min Act: -0.0000

Data Index: 1474719 (Python Code)

Max Activating Token Index: 25

Text #9

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2370. Min Act: -0.0000

Data Index: 1501754 (Python Code)

Max Activating Token Index: 11

Text #10

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2370. Min Act: -0.0000

Data Index: 1577624 (Python Code)

Max Activating Token Index: 11

Text #11

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2222. Min Act: -0.0000

Data Index: 1524076 (Python Code)

Max Activating Token Index: 39

Text #12

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2375. Min Act: -0.0000

Data Index: 1397548 (Python Code)

Max Activating Token Index: 31

Text #13

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2227. Min Act: -0.0000

Data Index: 20316 (C4 (Web Text))

Max Activating Token Index: 320

Text #14

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2091. Min Act: -0.0000

Data Index: 1417606 (Python Code)

Max Activating Token Index: 22

Text #15

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2318. Min Act: -0.0000

Data Index: 1647410 (Python Code)

Max Activating Token Index: 28

Text #16

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2002. Min Act: -0.0000

Data Index: 1378747 (Python Code)

Max Activating Token Index: 71

Text #17

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2209. Min Act: -0.0000

Data Index: 283911 (C4 (Web Text))

Max Activating Token Index: 623

Text #18

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2120. Min Act: -0.0000

Data Index: 1548587 (Python Code)

Max Activating Token Index: 31

Text #19

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2287. Min Act: -0.0000

Data Index: 1632714 (Python Code)

Max Activating Token Index: 18