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

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

Neuron 2306 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.2707. Min Act: -0.0000

Data Index: 1543125 (Python Code)

Max Activating Token Index: 372

Text #1

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.2588. Min Act: -0.0000

Data Index: 1394286 (Python Code)

Max Activating Token Index: 139

Text #2

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.2129. Min Act: -0.0000

Data Index: 54350 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.2145. Min Act: -0.0000

Data Index: 1641170 (Python Code)

Max Activating Token Index: 620

Text #4

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.2060. Min Act: -0.0000

Data Index: 727139 (C4 (Web Text))

Max Activating Token Index: 617

Text #5

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.1926. Min Act: -0.0000

Data Index: 1311709 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.2125. Min Act: -0.0000

Data Index: 993138 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.1767. Min Act: -0.0000

Data Index: 1655793 (Python Code)

Max Activating Token Index: 707

Text #8

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.1942. Min Act: -0.0000

Data Index: 1467255 (Python Code)

Max Activating Token Index: 131

Text #9

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.1938. Min Act: -0.0000

Data Index: 504386 (C4 (Web Text))

Max Activating Token Index: 546

Text #10

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.1786. Min Act: -0.0000

Data Index: 1579163 (Python Code)

Max Activating Token Index: 992

Text #11

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.1739. Min Act: -0.0000

Data Index: 1490984 (Python Code)

Max Activating Token Index: 901

Text #12

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.1839. Min Act: -0.0000

Data Index: 164876 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.1961. Min Act: -0.0000

Data Index: 1435260 (Python Code)

Max Activating Token Index: 887

Text #14

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.1722. Min Act: -0.0000

Data Index: 1406414 (Python Code)

Max Activating Token Index: 975

Text #15

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.1710. Min Act: -0.0000

Data Index: 1449222 (Python Code)

Max Activating Token Index: 583

Text #16

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.1755. Min Act: -0.0000

Data Index: 1587693 (Python Code)

Max Activating Token Index: 969

Text #17

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.1796. Min Act: -0.0000

Data Index: 1365297 (Python Code)

Max Activating Token Index: 202

Text #18

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.1731. Min Act: -0.0000

Data Index: 1374484 (Python Code)

Max Activating Token Index: 92

Text #19

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.1604. Min Act: -0.0000

Data Index: 1598325 (Python Code)

Max Activating Token Index: 212