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

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

Neuron 3987 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8975. Min Range: -1.8975

Max Act: 1.8975. Min Act: -0.0000

Data Index: 1558794 (Python Code)

Max Activating Token Index: 32

Text #1

Max Range: 1.8975. Min Range: -1.8975

Max Act: 1.8975. Min Act: 0.0000

Data Index: 1367868 (Python Code)

Max Activating Token Index: 32

Text #2

Max Range: 1.8975. Min Range: -1.8975

Max Act: 1.8975. Min Act: -0.0000

Data Index: 1649101 (Python Code)

Max Activating Token Index: 32

Text #3

Max Range: 1.8975. Min Range: -1.8975

Max Act: 1.7030. Min Act: -0.0000

Data Index: 1515187 (Python Code)

Max Activating Token Index: 360

Text #4

Max Range: 1.8975. Min Range: -1.8975

Max Act: 1.5560. Min Act: -0.0000

Data Index: 1587064 (Python Code)

Max Activating Token Index: 54

Text #5

Max Range: 1.8975. Min Range: -1.8975

Max Act: 1.5566. Min Act: -0.0000

Data Index: 1517908 (Python Code)

Max Activating Token Index: 676

Text #6

Max Range: 1.8975. Min Range: -1.8975

Max Act: 1.5779. Min Act: -0.0000

Data Index: 1392029 (Python Code)

Max Activating Token Index: 435

Text #7

Max Range: 1.8975. Min Range: -1.8975

Max Act: 1.4786. Min Act: 0.0000

Data Index: 1431893 (Python Code)

Max Activating Token Index: 762

Text #8

Max Range: 1.8975. Min Range: -1.8975

Max Act: 1.5573. Min Act: -0.0000

Data Index: 1644401 (Python Code)

Max Activating Token Index: 572

Text #9

Max Range: 1.8975. Min Range: -1.8975

Max Act: 1.4798. Min Act: -0.0000

Data Index: 1394656 (Python Code)

Max Activating Token Index: 147

Text #10

Max Range: 1.8975. Min Range: -1.8975

Max Act: 1.4233. Min Act: -0.0000

Data Index: 1626362 (Python Code)

Max Activating Token Index: 168

Text #11

Max Range: 1.8975. Min Range: -1.8975

Max Act: 1.4663. Min Act: -0.0000

Data Index: 1367421 (Python Code)

Max Activating Token Index: 30

Text #12

Max Range: 1.8975. Min Range: -1.8975

Max Act: 1.4527. Min Act: -0.0000

Data Index: 1631799 (Python Code)

Max Activating Token Index: 857

Text #13

Max Range: 1.8975. Min Range: -1.8975

Max Act: 1.3537. Min Act: -0.0000

Data Index: 1391542 (Python Code)

Max Activating Token Index: 748

Text #14

Max Range: 1.8975. Min Range: -1.8975

Max Act: 1.4191. Min Act: -0.0000

Data Index: 116788 (C4 (Web Text))

Max Activating Token Index: 51

Text #15

Max Range: 1.8975. Min Range: -1.8975

Max Act: 1.4173. Min Act: -0.0000

Data Index: 1371991 (Python Code)

Max Activating Token Index: 47

Text #16

Max Range: 1.8975. Min Range: -1.8975

Max Act: 1.3967. Min Act: -0.0000

Data Index: 1645769 (Python Code)

Max Activating Token Index: 578

Text #17

Max Range: 1.8975. Min Range: -1.8975

Max Act: 1.3938. Min Act: -0.0000

Data Index: 1526844 (Python Code)

Max Activating Token Index: 192

Text #18

Max Range: 1.8975. Min Range: -1.8975

Max Act: 1.3499. Min Act: -0.0000

Data Index: 1387893 (Python Code)

Max Activating Token Index: 272

Text #19

Max Range: 1.8975. Min Range: -1.8975

Max Act: 1.4292. Min Act: -0.0000

Data Index: 1435233 (Python Code)

Max Activating Token Index: 745