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

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

Neuron 918 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: 0.2969. Min Range: -0.2969

Max Act: 0.2558. Min Act: -0.0000

Data Index: 949504 (C4 (Web Text))

Max Activating Token Index: 943

Text #1

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2969. Min Act: -0.0000

Data Index: 1573974 (Python Code)

Max Activating Token Index: 905

Text #2

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2811. Min Act: -0.0000

Data Index: 672548 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2155. Min Act: -0.0000

Data Index: 437095 (C4 (Web Text))

Max Activating Token Index: 512

Text #4

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2108. Min Act: -0.0000

Data Index: 1505514 (Python Code)

Max Activating Token Index: 943

Text #5

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2135. Min Act: -0.0000

Data Index: 604483 (C4 (Web Text))

Max Activating Token Index: 566

Text #6

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2188. Min Act: -0.0000

Data Index: 536560 (C4 (Web Text))

Max Activating Token Index: 115

Text #7

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2023. Min Act: -0.0000

Data Index: 665781 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2168. Min Act: -0.0000

Data Index: 1562734 (Python Code)

Max Activating Token Index: 950

Text #9

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.1989. Min Act: -0.0000

Data Index: 155899 (C4 (Web Text))

Max Activating Token Index: 603

Text #10

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2053. Min Act: -0.0000

Data Index: 1311300 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.1702. Min Act: -0.0000

Data Index: 131670 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.1754. Min Act: -0.0000

Data Index: 1498750 (Python Code)

Max Activating Token Index: 649

Text #13

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.1856. Min Act: -0.0000

Data Index: 168972 (C4 (Web Text))

Max Activating Token Index: 25

Text #14

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.1860. Min Act: -0.0000

Data Index: 1144249 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.1767. Min Act: -0.0000

Data Index: 1110382 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.1651. Min Act: -0.0000

Data Index: 1375107 (Python Code)

Max Activating Token Index: 225

Text #17

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.1480. Min Act: -0.0000

Data Index: 1446083 (Python Code)

Max Activating Token Index: 762

Text #18

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2005. Min Act: -0.0000

Data Index: 1012559 (C4 (Web Text))

Max Activating Token Index: 779

Text #19

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.1916. Min Act: -0.0000

Data Index: 1489445 (Python Code)

Max Activating Token Index: 675