Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3416 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0629. Min Range: -1.0629

Max Act: 1.0629. Min Act: -0.0001

Data Index: 1616527 (Python Code)

Max Activating Token Index: 9

Text #1

Max Range: 1.0629. Min Range: -1.0629

Max Act: 0.9510. Min Act: -0.0001

Data Index: 1382487 (Python Code)

Max Activating Token Index: 7

Text #2

Max Range: 1.0629. Min Range: -1.0629

Max Act: 0.8519. Min Act: -0.0001

Data Index: 1488327 (Python Code)

Max Activating Token Index: 6

Text #3

Max Range: 1.0629. Min Range: -1.0629

Max Act: 0.8324. Min Act: -0.0001

Data Index: 1511897 (Python Code)

Max Activating Token Index: 6

Text #4

Max Range: 1.0629. Min Range: -1.0629

Max Act: 0.8324. Min Act: -0.0001

Data Index: 1411600 (Python Code)

Max Activating Token Index: 6

Text #5

Max Range: 1.0629. Min Range: -1.0629

Max Act: 0.6656. Min Act: -0.0001

Data Index: 1429304 (Python Code)

Max Activating Token Index: 7

Text #6

Max Range: 1.0629. Min Range: -1.0629

Max Act: 0.6027. Min Act: -0.0000

Data Index: 1372149 (Python Code)

Max Activating Token Index: 8

Text #7

Max Range: 1.0629. Min Range: -1.0629

Max Act: 0.5383. Min Act: -0.0001

Data Index: 430301 (C4 (Web Text))

Max Activating Token Index: 161

Text #8

Max Range: 1.0629. Min Range: -1.0629

Max Act: 0.5151. Min Act: -0.0001

Data Index: 1372905 (Python Code)

Max Activating Token Index: 102

Text #9

Max Range: 1.0629. Min Range: -1.0629

Max Act: 0.5177. Min Act: -0.0001

Data Index: 1510918 (Python Code)

Max Activating Token Index: 162

Text #10

Max Range: 1.0629. Min Range: -1.0629

Max Act: 0.4704. Min Act: -0.0001

Data Index: 1410129 (Python Code)

Max Activating Token Index: 38

Text #11

Max Range: 1.0629. Min Range: -1.0629

Max Act: 0.5201. Min Act: -0.0001

Data Index: 1401499 (Python Code)

Max Activating Token Index: 37

Text #12

Max Range: 1.0629. Min Range: -1.0629

Max Act: 0.5363. Min Act: -0.0001

Data Index: 1627005 (Python Code)

Max Activating Token Index: 89

Text #13

Max Range: 1.0629. Min Range: -1.0629

Max Act: 0.5347. Min Act: -0.0001

Data Index: 1605644 (Python Code)

Max Activating Token Index: 29

Text #14

Max Range: 1.0629. Min Range: -1.0629

Max Act: 0.5262. Min Act: -0.0000

Data Index: 777285 (C4 (Web Text))

Max Activating Token Index: 137

Text #15

Max Range: 1.0629. Min Range: -1.0629

Max Act: 0.4871. Min Act: -0.0001

Data Index: 1371950 (Python Code)

Max Activating Token Index: 14

Text #16

Max Range: 1.0629. Min Range: -1.0629

Max Act: 0.5091. Min Act: -0.0001

Data Index: 1450106 (Python Code)

Max Activating Token Index: 35

Text #17

Max Range: 1.0629. Min Range: -1.0629

Max Act: 0.4894. Min Act: -0.0001

Data Index: 1531767 (Python Code)

Max Activating Token Index: 37

Text #18

Max Range: 1.0629. Min Range: -1.0629

Max Act: 0.4841. Min Act: -0.0001

Data Index: 1093954 (C4 (Web Text))

Max Activating Token Index: 1022

Text #19

Max Range: 1.0629. Min Range: -1.0629

Max Act: 0.4687. Min Act: -0.0001

Data Index: 1622496 (Python Code)

Max Activating Token Index: 750