Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2286 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.2310. Min Act: -0.0001

Data Index: 1447675 (Python Code)

Max Activating Token Index: 556

Text #1

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.2140. Min Act: -0.0001

Data Index: 94389 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.2114. Min Act: -0.0001

Data Index: 1602137 (Python Code)

Max Activating Token Index: 792

Text #3

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.2112. Min Act: -0.0001

Data Index: 1656127 (Python Code)

Max Activating Token Index: 785

Text #4

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.2103. Min Act: -0.0001

Data Index: 1377845 (Python Code)

Max Activating Token Index: 692

Text #5

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1997. Min Act: -0.0001

Data Index: 1458507 (Python Code)

Max Activating Token Index: 862

Text #6

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.2072. Min Act: -0.0001

Data Index: 1529612 (Python Code)

Max Activating Token Index: 410

Text #7

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.2075. Min Act: -0.0001

Data Index: 1449784 (Python Code)

Max Activating Token Index: 330

Text #8

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1984. Min Act: -0.0001

Data Index: 1421653 (Python Code)

Max Activating Token Index: 117

Text #9

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1978. Min Act: -0.0001

Data Index: 1433659 (Python Code)

Max Activating Token Index: 411

Text #10

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1917. Min Act: -0.0001

Data Index: 1377501 (Python Code)

Max Activating Token Index: 697

Text #11

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1968. Min Act: -0.0001

Data Index: 1513071 (Python Code)

Max Activating Token Index: 558

Text #12

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1951. Min Act: -0.0001

Data Index: 1471203 (Python Code)

Max Activating Token Index: 972

Text #13

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.2023. Min Act: -0.0001

Data Index: 1468628 (Python Code)

Max Activating Token Index: 987

Text #14

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.2016. Min Act: -0.0001

Data Index: 1641143 (Python Code)

Max Activating Token Index: 994

Text #15

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1992. Min Act: -0.0001

Data Index: 1555576 (Python Code)

Max Activating Token Index: 346

Text #16

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1997. Min Act: -0.0001

Data Index: 1409325 (Python Code)

Max Activating Token Index: 350

Text #17

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1988. Min Act: -0.0001

Data Index: 1628734 (Python Code)

Max Activating Token Index: 673

Text #18

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1979. Min Act: -0.0001

Data Index: 1436692 (Python Code)

Max Activating Token Index: 234

Text #19

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1784. Min Act: -0.0001

Data Index: 1586986 (Python Code)

Max Activating Token Index: 765