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

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

Neuron 192 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1386. Min Act: -0.0000

Data Index: 1525757 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1073. Min Act: -0.0000

Data Index: 1578933 (Python Code)

Max Activating Token Index: 646

Text #2

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1146. Min Act: -0.0000

Data Index: 1371280 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1084. Min Act: -0.0000

Data Index: 1388073 (Python Code)

Max Activating Token Index: 974

Text #4

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1029. Min Act: -0.0000

Data Index: 1632671 (Python Code)

Max Activating Token Index: 944

Text #5

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1097. Min Act: -0.0000

Data Index: 1625924 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.0972. Min Act: -0.0000

Data Index: 1526568 (Python Code)

Max Activating Token Index: 769

Text #7

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1067. Min Act: -0.0000

Data Index: 1642678 (Python Code)

Max Activating Token Index: 32

Text #8

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1067. Min Act: -0.0000

Data Index: 1577246 (Python Code)

Max Activating Token Index: 955

Text #9

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.0937. Min Act: -0.0000

Data Index: 1399721 (Python Code)

Max Activating Token Index: 592

Text #10

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1065. Min Act: -0.0000

Data Index: 1431160 (Python Code)

Max Activating Token Index: 220

Text #11

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.0972. Min Act: -0.0000

Data Index: 1619177 (Python Code)

Max Activating Token Index: 877

Text #12

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1015. Min Act: -0.0000

Data Index: 1565097 (Python Code)

Max Activating Token Index: 490

Text #13

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1056. Min Act: -0.0000

Data Index: 1394810 (Python Code)

Max Activating Token Index: 921

Text #14

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1009. Min Act: -0.0000

Data Index: 1525166 (Python Code)

Max Activating Token Index: 226

Text #15

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.0820. Min Act: -0.0000

Data Index: 1526712 (Python Code)

Max Activating Token Index: 802

Text #16

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.0947. Min Act: -0.0000

Data Index: 1223990 (C4 (Web Text))

Max Activating Token Index: 890

Text #17

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.0970. Min Act: -0.0000

Data Index: 1364842 (Python Code)

Max Activating Token Index: 349

Text #18

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1046. Min Act: -0.0000

Data Index: 1475610 (Python Code)

Max Activating Token Index: 355

Text #19

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.0968. Min Act: -0.0000

Data Index: 1452881 (Python Code)

Max Activating Token Index: 144