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

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

Neuron 679 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: 0.6052. Min Range: -0.6052

Max Act: 0.6052. Min Act: -0.0001

Data Index: 1588401 (Python Code)

Max Activating Token Index: 37

Text #1

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5961. Min Act: -0.0001

Data Index: 1418114 (Python Code)

Max Activating Token Index: 56

Text #2

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5918. Min Act: -0.0001

Data Index: 1599385 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5786. Min Act: -0.0001

Data Index: 1594684 (Python Code)

Max Activating Token Index: 41

Text #4

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5764. Min Act: -0.0001

Data Index: 1548599 (Python Code)

Max Activating Token Index: 64

Text #5

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5812. Min Act: -0.0001

Data Index: 1564652 (Python Code)

Max Activating Token Index: 53

Text #6

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5648. Min Act: -0.0001

Data Index: 1483056 (Python Code)

Max Activating Token Index: 63

Text #7

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5640. Min Act: -0.0001

Data Index: 1612961 (Python Code)

Max Activating Token Index: 46

Text #8

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5609. Min Act: -0.0001

Data Index: 1612389 (Python Code)

Max Activating Token Index: 27

Text #9

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5643. Min Act: -0.0001

Data Index: 1583494 (Python Code)

Max Activating Token Index: 10

Text #10

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5594. Min Act: -0.0001

Data Index: 1589442 (Python Code)

Max Activating Token Index: 69

Text #11

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5602. Min Act: -0.0002

Data Index: 1538372 (Python Code)

Max Activating Token Index: 23

Text #12

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5489. Min Act: -0.0001

Data Index: 1537090 (Python Code)

Max Activating Token Index: 52

Text #13

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5583. Min Act: -0.0001

Data Index: 1641143 (Python Code)

Max Activating Token Index: 52

Text #14

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5596. Min Act: -0.0001

Data Index: 1376627 (Python Code)

Max Activating Token Index: 36

Text #15

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5437. Min Act: -0.0001

Data Index: 1544485 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5505. Min Act: -0.0001

Data Index: 1646432 (Python Code)

Max Activating Token Index: 16

Text #17

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5342. Min Act: -0.0001

Data Index: 1540211 (Python Code)

Max Activating Token Index: 31

Text #18

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5357. Min Act: -0.0001

Data Index: 1643943 (Python Code)

Max Activating Token Index: 141

Text #19

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5369. Min Act: -0.0001

Data Index: 1502731 (Python Code)

Max Activating Token Index: 113