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

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

Neuron 1379 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2824. Min Range: -1.2824

Max Act: 1.2533. Min Act: -0.0001

Data Index: 1233608 (C4 (Web Text))

Max Activating Token Index: 425

Text #1

Max Range: 1.2824. Min Range: -1.2824

Max Act: 1.2824. Min Act: -0.0001

Data Index: 1268837 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 1.2824. Min Range: -1.2824

Max Act: 1.1542. Min Act: -0.0000

Data Index: 1522688 (Python Code)

Max Activating Token Index: 650

Text #3

Max Range: 1.2824. Min Range: -1.2824

Max Act: 1.1384. Min Act: -0.0000

Data Index: 913693 (C4 (Web Text))

Max Activating Token Index: 629

Text #4

Max Range: 1.2824. Min Range: -1.2824

Max Act: 1.1013. Min Act: -0.0001

Data Index: 904262 (C4 (Web Text))

Max Activating Token Index: 265

Text #5

Max Range: 1.2824. Min Range: -1.2824

Max Act: 1.0673. Min Act: -0.0000

Data Index: 1245767 (C4 (Web Text))

Max Activating Token Index: 948

Text #6

Max Range: 1.2824. Min Range: -1.2824

Max Act: 1.1006. Min Act: -0.0001

Data Index: 400682 (C4 (Web Text))

Max Activating Token Index: 184

Text #7

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.9558. Min Act: -0.0000

Data Index: 739508 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 1.2824. Min Range: -1.2824

Max Act: 1.0063. Min Act: -0.0000

Data Index: 1434256 (Python Code)

Max Activating Token Index: 566

Text #9

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.9670. Min Act: -0.0001

Data Index: 440950 (C4 (Web Text))

Max Activating Token Index: 386

Text #10

Max Range: 1.2824. Min Range: -1.2824

Max Act: 1.0912. Min Act: -0.0001

Data Index: 934380 (C4 (Web Text))

Max Activating Token Index: 918

Text #11

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.9678. Min Act: -0.0000

Data Index: 1365940 (Python Code)

Max Activating Token Index: 177

Text #12

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.9756. Min Act: -0.0001

Data Index: 128623 (C4 (Web Text))

Max Activating Token Index: 899

Text #13

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.9736. Min Act: -0.0000

Data Index: 1387292 (Python Code)

Max Activating Token Index: 659

Text #14

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.9621. Min Act: -0.0001

Data Index: 467381 (C4 (Web Text))

Max Activating Token Index: 845

Text #15

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.9724. Min Act: -0.0001

Data Index: 754405 (C4 (Web Text))

Max Activating Token Index: 262

Text #16

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.9374. Min Act: -0.0001

Data Index: 556968 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.9386. Min Act: -0.0000

Data Index: 1481970 (Python Code)

Max Activating Token Index: 168

Text #18

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.9231. Min Act: -0.0001

Data Index: 1104578 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.8946. Min Act: -0.0000

Data Index: 1354992 (C4 (Web Text))

Max Activating Token Index: 454