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

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

Neuron 2663 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: 1.0067. Min Range: -1.0067

Max Act: 1.0067. Min Act: -0.0001

Data Index: 1360882 (Python Code)

Max Activating Token Index: 638

Text #1

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.9652. Min Act: -0.0001

Data Index: 1549431 (Python Code)

Max Activating Token Index: 14

Text #2

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.9586. Min Act: -0.0001

Data Index: 1477780 (Python Code)

Max Activating Token Index: 496

Text #3

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.9480. Min Act: -0.0001

Data Index: 1647403 (Python Code)

Max Activating Token Index: 228

Text #4

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.9703. Min Act: -0.0000

Data Index: 1491530 (Python Code)

Max Activating Token Index: 815

Text #5

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.8790. Min Act: -0.0001

Data Index: 1519768 (Python Code)

Max Activating Token Index: 932

Text #6

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.9417. Min Act: -0.0001

Data Index: 1571374 (Python Code)

Max Activating Token Index: 158

Text #7

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.8808. Min Act: -0.0000

Data Index: 1634682 (Python Code)

Max Activating Token Index: 18

Text #8

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.8548. Min Act: -0.0001

Data Index: 1456492 (Python Code)

Max Activating Token Index: 499

Text #9

Max Range: 1.0067. Min Range: -1.0067

Max Act: 1.0053. Min Act: -0.0001

Data Index: 1636020 (Python Code)

Max Activating Token Index: 930

Text #10

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.9162. Min Act: -0.0001

Data Index: 1415509 (Python Code)

Max Activating Token Index: 426

Text #11

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.8292. Min Act: -0.0000

Data Index: 1631763 (Python Code)

Max Activating Token Index: 574

Text #12

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.8913. Min Act: -0.0000

Data Index: 1588679 (Python Code)

Max Activating Token Index: 106

Text #13

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.8768. Min Act: -0.0000

Data Index: 1509340 (Python Code)

Max Activating Token Index: 116

Text #14

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.8948. Min Act: -0.0000

Data Index: 1489879 (Python Code)

Max Activating Token Index: 298

Text #15

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.8742. Min Act: -0.0000

Data Index: 1423340 (Python Code)

Max Activating Token Index: 423

Text #16

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.8656. Min Act: -0.0000

Data Index: 1588232 (Python Code)

Max Activating Token Index: 281

Text #17

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.8540. Min Act: -0.0000

Data Index: 1655362 (Python Code)

Max Activating Token Index: 894

Text #18

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.8866. Min Act: -0.0000

Data Index: 1489679 (Python Code)

Max Activating Token Index: 985

Text #19

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.7897. Min Act: -0.0001

Data Index: 1435043 (Python Code)

Max Activating Token Index: 512