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

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

Neuron 5642 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: 0.9595. Min Range: -0.9595

Max Act: 0.9595. Min Act: -0.0002

Data Index: 1480341 (Python Code)

Max Activating Token Index: 28

Text #1

Max Range: 0.9595. Min Range: -0.9595

Max Act: 0.9201. Min Act: -0.0001

Data Index: 1450352 (Python Code)

Max Activating Token Index: 15

Text #2

Max Range: 0.9595. Min Range: -0.9595

Max Act: 0.9257. Min Act: -0.0001

Data Index: 1564183 (Python Code)

Max Activating Token Index: 25

Text #3

Max Range: 0.9595. Min Range: -0.9595

Max Act: 0.9167. Min Act: -0.0001

Data Index: 1578552 (Python Code)

Max Activating Token Index: 5

Text #4

Max Range: 0.9595. Min Range: -0.9595

Max Act: 0.8852. Min Act: -0.0001

Data Index: 1580601 (Python Code)

Max Activating Token Index: 30

Text #5

Max Range: 0.9595. Min Range: -0.9595

Max Act: 0.8661. Min Act: -0.0001

Data Index: 1654261 (Python Code)

Max Activating Token Index: 49

Text #6

Max Range: 0.9595. Min Range: -0.9595

Max Act: 0.8869. Min Act: -0.0001

Data Index: 1587284 (Python Code)

Max Activating Token Index: 6

Text #7

Max Range: 0.9595. Min Range: -0.9595

Max Act: 0.8658. Min Act: -0.0001

Data Index: 1419630 (Python Code)

Max Activating Token Index: 4

Text #8

Max Range: 0.9595. Min Range: -0.9595

Max Act: 0.8594. Min Act: -0.0001

Data Index: 1647032 (Python Code)

Max Activating Token Index: 74

Text #9

Max Range: 0.9595. Min Range: -0.9595

Max Act: 0.8382. Min Act: -0.0001

Data Index: 1518841 (Python Code)

Max Activating Token Index: 13

Text #10

Max Range: 0.9595. Min Range: -0.9595

Max Act: 0.8439. Min Act: -0.0001

Data Index: 1613672 (Python Code)

Max Activating Token Index: 95

Text #11

Max Range: 0.9595. Min Range: -0.9595

Max Act: 0.8317. Min Act: -0.0001

Data Index: 1611540 (Python Code)

Max Activating Token Index: 4

Text #12

Max Range: 0.9595. Min Range: -0.9595

Max Act: 0.8332. Min Act: -0.0001

Data Index: 1376017 (Python Code)

Max Activating Token Index: 754

Text #13

Max Range: 0.9595. Min Range: -0.9595

Max Act: 0.8281. Min Act: -0.0001

Data Index: 1493525 (Python Code)

Max Activating Token Index: 55

Text #14

Max Range: 0.9595. Min Range: -0.9595

Max Act: 0.8214. Min Act: -0.0001

Data Index: 1361925 (Python Code)

Max Activating Token Index: 13

Text #15

Max Range: 0.9595. Min Range: -0.9595

Max Act: 0.8246. Min Act: -0.0001

Data Index: 1437115 (Python Code)

Max Activating Token Index: 93

Text #16

Max Range: 0.9595. Min Range: -0.9595

Max Act: 0.8264. Min Act: -0.0001

Data Index: 1620090 (Python Code)

Max Activating Token Index: 51

Text #17

Max Range: 0.9595. Min Range: -0.9595

Max Act: 0.8146. Min Act: -0.0002

Data Index: 1513272 (Python Code)

Max Activating Token Index: 12

Text #18

Max Range: 0.9595. Min Range: -0.9595

Max Act: 0.8246. Min Act: -0.0001

Data Index: 1528776 (Python Code)

Max Activating Token Index: 80

Text #19

Max Range: 0.9595. Min Range: -0.9595

Max Act: 0.8263. Min Act: -0.0001

Data Index: 1431841 (Python Code)

Max Activating Token Index: 16