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

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

Neuron 634 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: 0.5961. Min Range: -0.5961

Max Act: 0.5938. Min Act: -0.0001

Data Index: 1379669 (Python Code)

Max Activating Token Index: 63

Text #1

Max Range: 0.5961. Min Range: -0.5961

Max Act: 0.5961. Min Act: -0.0001

Data Index: 1431886 (Python Code)

Max Activating Token Index: 60

Text #2

Max Range: 0.5961. Min Range: -0.5961

Max Act: 0.5525. Min Act: -0.0001

Data Index: 1643943 (Python Code)

Max Activating Token Index: 22

Text #3

Max Range: 0.5961. Min Range: -0.5961

Max Act: 0.5231. Min Act: -0.0001

Data Index: 1392832 (Python Code)

Max Activating Token Index: 123

Text #4

Max Range: 0.5961. Min Range: -0.5961

Max Act: 0.4890. Min Act: -0.0001

Data Index: 1556918 (Python Code)

Max Activating Token Index: 95

Text #5

Max Range: 0.5961. Min Range: -0.5961

Max Act: 0.4906. Min Act: -0.0001

Data Index: 1503938 (Python Code)

Max Activating Token Index: 23

Text #6

Max Range: 0.5961. Min Range: -0.5961

Max Act: 0.4783. Min Act: -0.0001

Data Index: 1636963 (Python Code)

Max Activating Token Index: 21

Text #7

Max Range: 0.5961. Min Range: -0.5961

Max Act: 0.4769. Min Act: -0.0001

Data Index: 1546171 (Python Code)

Max Activating Token Index: 91

Text #8

Max Range: 0.5961. Min Range: -0.5961

Max Act: 0.4732. Min Act: -0.0001

Data Index: 1521031 (Python Code)

Max Activating Token Index: 9

Text #9

Max Range: 0.5961. Min Range: -0.5961

Max Act: 0.4615. Min Act: -0.0001

Data Index: 1551973 (Python Code)

Max Activating Token Index: 392

Text #10

Max Range: 0.5961. Min Range: -0.5961

Max Act: 0.4619. Min Act: -0.0001

Data Index: 1522132 (Python Code)

Max Activating Token Index: 25

Text #11

Max Range: 0.5961. Min Range: -0.5961

Max Act: 0.4629. Min Act: -0.0001

Data Index: 1564374 (Python Code)

Max Activating Token Index: 314

Text #12

Max Range: 0.5961. Min Range: -0.5961

Max Act: 0.4417. Min Act: -0.0001

Data Index: 1384925 (Python Code)

Max Activating Token Index: 22

Text #13

Max Range: 0.5961. Min Range: -0.5961

Max Act: 0.4416. Min Act: -0.0001

Data Index: 1390819 (Python Code)

Max Activating Token Index: 209

Text #14

Max Range: 0.5961. Min Range: -0.5961

Max Act: 0.4338. Min Act: -0.0001

Data Index: 1500887 (Python Code)

Max Activating Token Index: 394

Text #15

Max Range: 0.5961. Min Range: -0.5961

Max Act: 0.4381. Min Act: -0.0001

Data Index: 1360887 (Python Code)

Max Activating Token Index: 615

Text #16

Max Range: 0.5961. Min Range: -0.5961

Max Act: 0.4224. Min Act: -0.0001

Data Index: 1477530 (Python Code)

Max Activating Token Index: 9

Text #17

Max Range: 0.5961. Min Range: -0.5961

Max Act: 0.4147. Min Act: -0.0001

Data Index: 1562020 (Python Code)

Max Activating Token Index: 935

Text #18

Max Range: 0.5961. Min Range: -0.5961

Max Act: 0.4220. Min Act: -0.0000

Data Index: 1583474 (Python Code)

Max Activating Token Index: 333

Text #19

Max Range: 0.5961. Min Range: -0.5961

Max Act: 0.4108. Min Act: -0.0001

Data Index: 1389993 (Python Code)

Max Activating Token Index: 83