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

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

Neuron 1121 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9422. Min Range: -2.9422

Max Act: 2.9422. Min Act: -0.0000

Data Index: 1596334 (Python Code)

Max Activating Token Index: 45

Text #1

Max Range: 2.9422. Min Range: -2.9422

Max Act: 2.9144. Min Act: -0.0000

Data Index: 1653465 (Python Code)

Max Activating Token Index: 80

Text #2

Max Range: 2.9422. Min Range: -2.9422

Max Act: 2.6377. Min Act: -0.0000

Data Index: 1613045 (Python Code)

Max Activating Token Index: 58

Text #3

Max Range: 2.9422. Min Range: -2.9422

Max Act: 2.7724. Min Act: -0.0000

Data Index: 1571501 (Python Code)

Max Activating Token Index: 48

Text #4

Max Range: 2.9422. Min Range: -2.9422

Max Act: 2.8453. Min Act: -0.0000

Data Index: 1441353 (Python Code)

Max Activating Token Index: 37

Text #5

Max Range: 2.9422. Min Range: -2.9422

Max Act: 2.6994. Min Act: -0.0000

Data Index: 1373815 (Python Code)

Max Activating Token Index: 54

Text #6

Max Range: 2.9422. Min Range: -2.9422

Max Act: 2.6633. Min Act: -0.0000

Data Index: 1589968 (Python Code)

Max Activating Token Index: 388

Text #7

Max Range: 2.9422. Min Range: -2.9422

Max Act: 2.6059. Min Act: -0.0000

Data Index: 1481690 (Python Code)

Max Activating Token Index: 294

Text #8

Max Range: 2.9422. Min Range: -2.9422

Max Act: 2.5846. Min Act: -0.0000

Data Index: 1430882 (Python Code)

Max Activating Token Index: 49

Text #9

Max Range: 2.9422. Min Range: -2.9422

Max Act: 2.6699. Min Act: -0.0000

Data Index: 1570080 (Python Code)

Max Activating Token Index: 1006

Text #10

Max Range: 2.9422. Min Range: -2.9422

Max Act: 2.6002. Min Act: -0.0000

Data Index: 1453837 (Python Code)

Max Activating Token Index: 156

Text #11

Max Range: 2.9422. Min Range: -2.9422

Max Act: 2.4641. Min Act: -0.0000

Data Index: 1388104 (Python Code)

Max Activating Token Index: 230

Text #12

Max Range: 2.9422. Min Range: -2.9422

Max Act: 2.3274. Min Act: -0.0000

Data Index: 1431078 (Python Code)

Max Activating Token Index: 305

Text #13

Max Range: 2.9422. Min Range: -2.9422

Max Act: 2.4514. Min Act: -0.0000

Data Index: 1597145 (Python Code)

Max Activating Token Index: 5

Text #14

Max Range: 2.9422. Min Range: -2.9422

Max Act: 2.4514. Min Act: -0.0000

Data Index: 1414899 (Python Code)

Max Activating Token Index: 5

Text #15

Max Range: 2.9422. Min Range: -2.9422

Max Act: 2.4144. Min Act: -0.0000

Data Index: 1397867 (Python Code)

Max Activating Token Index: 763

Text #16

Max Range: 2.9422. Min Range: -2.9422

Max Act: 2.2362. Min Act: -0.0000

Data Index: 1597786 (Python Code)

Max Activating Token Index: 578

Text #17

Max Range: 2.9422. Min Range: -2.9422

Max Act: 2.3598. Min Act: -0.0000

Data Index: 1652173 (Python Code)

Max Activating Token Index: 230

Text #18

Max Range: 2.9422. Min Range: -2.9422

Max Act: 2.3359. Min Act: -0.0000

Data Index: 1457303 (Python Code)

Max Activating Token Index: 34

Text #19

Max Range: 2.9422. Min Range: -2.9422

Max Act: 2.2142. Min Act: -0.0000

Data Index: 1507819 (Python Code)

Max Activating Token Index: 440