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

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

Neuron 8 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.7058. Min Range: -4.7058

Max Act: 4.6453. Min Act: -0.0000

Data Index: 1609445 (Python Code)

Max Activating Token Index: 819

Text #1

Max Range: 4.7058. Min Range: -4.7058

Max Act: 4.7058. Min Act: -0.0000

Data Index: 1626216 (Python Code)

Max Activating Token Index: 574

Text #2

Max Range: 4.7058. Min Range: -4.7058

Max Act: 4.5437. Min Act: -0.0000

Data Index: 1535721 (Python Code)

Max Activating Token Index: 354

Text #3

Max Range: 4.7058. Min Range: -4.7058

Max Act: 4.2063. Min Act: -0.0000

Data Index: 1388715 (Python Code)

Max Activating Token Index: 827

Text #4

Max Range: 4.7058. Min Range: -4.7058

Max Act: 4.2293. Min Act: -0.0000

Data Index: 1603580 (Python Code)

Max Activating Token Index: 604

Text #5

Max Range: 4.7058. Min Range: -4.7058

Max Act: 3.9915. Min Act: -0.0000

Data Index: 1502472 (Python Code)

Max Activating Token Index: 45

Text #6

Max Range: 4.7058. Min Range: -4.7058

Max Act: 3.8681. Min Act: -0.0000

Data Index: 1375969 (Python Code)

Max Activating Token Index: 988

Text #7

Max Range: 4.7058. Min Range: -4.7058

Max Act: 3.8682. Min Act: -0.0000

Data Index: 1485600 (Python Code)

Max Activating Token Index: 465

Text #8

Max Range: 4.7058. Min Range: -4.7058

Max Act: 3.7617. Min Act: -0.0000

Data Index: 1392761 (Python Code)

Max Activating Token Index: 282

Text #9

Max Range: 4.7058. Min Range: -4.7058

Max Act: 3.5110. Min Act: -0.0000

Data Index: 1645819 (Python Code)

Max Activating Token Index: 12

Text #10

Max Range: 4.7058. Min Range: -4.7058

Max Act: 3.5078. Min Act: -0.0000

Data Index: 1537421 (Python Code)

Max Activating Token Index: 746

Text #11

Max Range: 4.7058. Min Range: -4.7058

Max Act: 3.4557. Min Act: -0.0000

Data Index: 1426410 (Python Code)

Max Activating Token Index: 17

Text #12

Max Range: 4.7058. Min Range: -4.7058

Max Act: 3.4888. Min Act: -0.0000

Data Index: 1567412 (Python Code)

Max Activating Token Index: 516

Text #13

Max Range: 4.7058. Min Range: -4.7058

Max Act: 3.4614. Min Act: -0.0000

Data Index: 1465665 (Python Code)

Max Activating Token Index: 295

Text #14

Max Range: 4.7058. Min Range: -4.7058

Max Act: 3.6351. Min Act: -0.0000

Data Index: 1480071 (Python Code)

Max Activating Token Index: 694

Text #15

Max Range: 4.7058. Min Range: -4.7058

Max Act: 3.4556. Min Act: -0.0000

Data Index: 1471756 (Python Code)

Max Activating Token Index: 124

Text #16

Max Range: 4.7058. Min Range: -4.7058

Max Act: 3.4295. Min Act: -0.0000

Data Index: 1417553 (Python Code)

Max Activating Token Index: 105

Text #17

Max Range: 4.7058. Min Range: -4.7058

Max Act: 3.3853. Min Act: -0.0000

Data Index: 1644472 (Python Code)

Max Activating Token Index: 16

Text #18

Max Range: 4.7058. Min Range: -4.7058

Max Act: 3.3735. Min Act: -0.0000

Data Index: 1515882 (Python Code)

Max Activating Token Index: 633

Text #19

Max Range: 4.7058. Min Range: -4.7058

Max Act: 3.1850. Min Act: -0.0000

Data Index: 1379631 (Python Code)

Max Activating Token Index: 102