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

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

Neuron 3048 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.6223. Min Range: -0.6223

Max Act: 0.6223. Min Act: -0.0001

Data Index: 1483993 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.6223. Min Range: -0.6223

Max Act: 0.5980. Min Act: -0.0001

Data Index: 1524972 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.6223. Min Range: -0.6223

Max Act: 0.5550. Min Act: -0.0001

Data Index: 1599035 (Python Code)

Max Activating Token Index: 14

Text #3

Max Range: 0.6223. Min Range: -0.6223

Max Act: 0.5333. Min Act: -0.0001

Data Index: 1521365 (Python Code)

Max Activating Token Index: 626

Text #4

Max Range: 0.6223. Min Range: -0.6223

Max Act: 0.5234. Min Act: -0.0001

Data Index: 1584089 (Python Code)

Max Activating Token Index: 19

Text #5

Max Range: 0.6223. Min Range: -0.6223

Max Act: 0.5234. Min Act: -0.0002

Data Index: 1602116 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.6223. Min Range: -0.6223

Max Act: 0.5217. Min Act: -0.0001

Data Index: 1623578 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.6223. Min Range: -0.6223

Max Act: 0.5130. Min Act: -0.0002

Data Index: 1500976 (Python Code)

Max Activating Token Index: 12

Text #8

Max Range: 0.6223. Min Range: -0.6223

Max Act: 0.5087. Min Act: -0.0001

Data Index: 1621643 (Python Code)

Max Activating Token Index: 50

Text #9

Max Range: 0.6223. Min Range: -0.6223

Max Act: 0.5172. Min Act: -0.0001

Data Index: 1447739 (Python Code)

Max Activating Token Index: 8

Text #10

Max Range: 0.6223. Min Range: -0.6223

Max Act: 0.5112. Min Act: -0.0001

Data Index: 1540724 (Python Code)

Max Activating Token Index: 24

Text #11

Max Range: 0.6223. Min Range: -0.6223

Max Act: 0.5038. Min Act: -0.0001

Data Index: 1613211 (Python Code)

Max Activating Token Index: 33

Text #12

Max Range: 0.6223. Min Range: -0.6223

Max Act: 0.5052. Min Act: -0.0001

Data Index: 1567371 (Python Code)

Max Activating Token Index: 12

Text #13

Max Range: 0.6223. Min Range: -0.6223

Max Act: 0.5060. Min Act: -0.0001

Data Index: 1424304 (Python Code)

Max Activating Token Index: 54

Text #14

Max Range: 0.6223. Min Range: -0.6223

Max Act: 0.5040. Min Act: -0.0001

Data Index: 1645927 (Python Code)

Max Activating Token Index: 6

Text #15

Max Range: 0.6223. Min Range: -0.6223

Max Act: 0.5090. Min Act: -0.0002

Data Index: 1486412 (Python Code)

Max Activating Token Index: 27

Text #16

Max Range: 0.6223. Min Range: -0.6223

Max Act: 0.5008. Min Act: -0.0001

Data Index: 1481516 (Python Code)

Max Activating Token Index: 494

Text #17

Max Range: 0.6223. Min Range: -0.6223

Max Act: 0.5035. Min Act: -0.0001

Data Index: 1494520 (Python Code)

Max Activating Token Index: 152

Text #18

Max Range: 0.6223. Min Range: -0.6223

Max Act: 0.5040. Min Act: -0.0001

Data Index: 1498243 (Python Code)

Max Activating Token Index: 17

Text #19

Max Range: 0.6223. Min Range: -0.6223

Max Act: 0.5003. Min Act: -0.0001

Data Index: 1557419 (Python Code)

Max Activating Token Index: 74