Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1372 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.6589. Min Act: -0.0000

Data Index: 1514984 (Python Code)

Max Activating Token Index: 24

Text #1

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.5487. Min Act: -0.0000

Data Index: 1609085 (Python Code)

Max Activating Token Index: 13

Text #2

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.5405. Min Act: 0.0001

Data Index: 1644443 (Python Code)

Max Activating Token Index: 12

Text #3

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.5306. Min Act: -0.0000

Data Index: 1411038 (Python Code)

Max Activating Token Index: 28

Text #4

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.4790. Min Act: -0.0000

Data Index: 1612358 (Python Code)

Max Activating Token Index: 116

Text #5

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.4979. Min Act: -0.0000

Data Index: 1571984 (Python Code)

Max Activating Token Index: 752

Text #6

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.4658. Min Act: -0.0000

Data Index: 1569103 (Python Code)

Max Activating Token Index: 33

Text #7

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.4288. Min Act: -0.0000

Data Index: 1579347 (Python Code)

Max Activating Token Index: 210

Text #8

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.4370. Min Act: -0.0000

Data Index: 1547144 (Python Code)

Max Activating Token Index: 941

Text #9

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.4318. Min Act: -0.0000

Data Index: 1516453 (Python Code)

Max Activating Token Index: 170

Text #10

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.4448. Min Act: 0.0001

Data Index: 1618236 (Python Code)

Max Activating Token Index: 12

Text #11

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.4549. Min Act: -0.0000

Data Index: 1618993 (Python Code)

Max Activating Token Index: 114

Text #12

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.4258. Min Act: -0.0000

Data Index: 1416931 (Python Code)

Max Activating Token Index: 379

Text #13

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.4386. Min Act: -0.0000

Data Index: 1588042 (Python Code)

Max Activating Token Index: 985

Text #14

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.4311. Min Act: -0.0000

Data Index: 1489916 (Python Code)

Max Activating Token Index: 64

Text #15

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.4253. Min Act: -0.0000

Data Index: 1395387 (Python Code)

Max Activating Token Index: 832

Text #16

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.4125. Min Act: -0.0000

Data Index: 1385245 (Python Code)

Max Activating Token Index: 28

Text #17

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.4132. Min Act: 0.0000

Data Index: 1469935 (Python Code)

Max Activating Token Index: 41

Text #18

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.3957. Min Act: 0.0000

Data Index: 1584501 (Python Code)

Max Activating Token Index: 103

Text #19

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.3952. Min Act: -0.0000

Data Index: 1432698 (Python Code)

Max Activating Token Index: 23