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

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

Neuron 3665 in Layer 1

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: 0.1057. Min Range: -0.1057

Max Act: 0.1057. Min Act: -0.0002

Data Index: 1271768 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.1024. Min Act: -0.0002

Data Index: 1607023 (Python Code)

Max Activating Token Index: 4

Text #2

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.1013. Min Act: -0.0002

Data Index: 420122 (C4 (Web Text))

Max Activating Token Index: 786

Text #3

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.1015. Min Act: -0.0002

Data Index: 574964 (C4 (Web Text))

Max Activating Token Index: 290

Text #4

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.1010. Min Act: -0.0002

Data Index: 878385 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0981. Min Act: -0.0002

Data Index: 46615 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0975. Min Act: -0.0002

Data Index: 1265718 (C4 (Web Text))

Max Activating Token Index: 481

Text #7

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0984. Min Act: -0.0002

Data Index: 392094 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0987. Min Act: -0.0002

Data Index: 272852 (C4 (Web Text))

Max Activating Token Index: 823

Text #9

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0978. Min Act: -0.0002

Data Index: 1065418 (C4 (Web Text))

Max Activating Token Index: 284

Text #10

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0986. Min Act: -0.0002

Data Index: 860561 (C4 (Web Text))

Max Activating Token Index: 878

Text #11

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0958. Min Act: -0.0002

Data Index: 1147092 (C4 (Web Text))

Max Activating Token Index: 427

Text #12

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0976. Min Act: -0.0002

Data Index: 180541 (C4 (Web Text))

Max Activating Token Index: 541

Text #13

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0969. Min Act: -0.0002

Data Index: 697079 (C4 (Web Text))

Max Activating Token Index: 488

Text #14

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0944. Min Act: -0.0002

Data Index: 982345 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0943. Min Act: -0.0002

Data Index: 1334887 (C4 (Web Text))

Max Activating Token Index: 383

Text #16

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0968. Min Act: -0.0003

Data Index: 469041 (C4 (Web Text))

Max Activating Token Index: 318

Text #17

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0950. Min Act: -0.0002

Data Index: 1477731 (Python Code)

Max Activating Token Index: 86

Text #18

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0953. Min Act: -0.0002

Data Index: 987370 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0944. Min Act: -0.0002

Data Index: 1137037 (C4 (Web Text))

Max Activating Token Index: 677