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

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

Neuron 340 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0066. Min Act: -0.0002

Data Index: 1485984 (Python Code)

Max Activating Token Index: 39

Text #1

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0065. Min Act: -0.0002

Data Index: 1445398 (Python Code)

Max Activating Token Index: 106

Text #2

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0064. Min Act: -0.0002

Data Index: 558918 (C4 (Web Text))

Max Activating Token Index: 4

Text #3

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0062. Min Act: -0.0002

Data Index: 1476625 (Python Code)

Max Activating Token Index: 1

Text #4

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0062. Min Act: -0.0002

Data Index: 1389234 (Python Code)

Max Activating Token Index: 1

Text #5

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0063. Min Act: -0.0002

Data Index: 690148 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0062. Min Act: -0.0002

Data Index: 1197572 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0061. Min Act: -0.0002

Data Index: 589015 (C4 (Web Text))

Max Activating Token Index: 417

Text #8

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0061. Min Act: -0.0002

Data Index: 573570 (C4 (Web Text))

Max Activating Token Index: 279

Text #9

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0061. Min Act: -0.0002

Data Index: 22034 (C4 (Web Text))

Max Activating Token Index: 525

Text #10

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0060. Min Act: -0.0002

Data Index: 30954 (C4 (Web Text))

Max Activating Token Index: 901

Text #11

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0060. Min Act: -0.0002

Data Index: 1040774 (C4 (Web Text))

Max Activating Token Index: 917

Text #12

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0060. Min Act: -0.0002

Data Index: 1376154 (Python Code)

Max Activating Token Index: 71

Text #13

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0059. Min Act: -0.0002

Data Index: 1504469 (Python Code)

Max Activating Token Index: 867

Text #14

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0060. Min Act: -0.0002

Data Index: 1565664 (Python Code)

Max Activating Token Index: 36

Text #15

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0060. Min Act: -0.0002

Data Index: 636516 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0061. Min Act: -0.0002

Data Index: 1634483 (Python Code)

Max Activating Token Index: 170

Text #17

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0059. Min Act: -0.0002

Data Index: 695197 (C4 (Web Text))

Max Activating Token Index: 382

Text #18

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0059. Min Act: -0.0002

Data Index: 1504892 (Python Code)

Max Activating Token Index: 17

Text #19

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0059. Min Act: -0.0002

Data Index: 1609820 (Python Code)

Max Activating Token Index: 46