Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2850 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.2101. Min Act: -0.0000

Data Index: 1064409 (C4 (Web Text))

Max Activating Token Index: 978

Text #1

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.2007. Min Act: -0.0000

Data Index: 630948 (C4 (Web Text))

Max Activating Token Index: 615

Text #2

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.2036. Min Act: -0.0001

Data Index: 1314673 (C4 (Web Text))

Max Activating Token Index: 884

Text #3

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.2021. Min Act: -0.0001

Data Index: 609223 (C4 (Web Text))

Max Activating Token Index: 856

Text #4

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.2082. Min Act: -0.0000

Data Index: 615264 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.2017. Min Act: -0.0000

Data Index: 135536 (C4 (Web Text))

Max Activating Token Index: 729

Text #6

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1994. Min Act: -0.0001

Data Index: 454489 (C4 (Web Text))

Max Activating Token Index: 876

Text #7

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1968. Min Act: -0.0001

Data Index: 171113 (C4 (Web Text))

Max Activating Token Index: 894

Text #8

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1867. Min Act: -0.0000

Data Index: 92851 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1923. Min Act: -0.0001

Data Index: 1066599 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1831. Min Act: -0.0000

Data Index: 601456 (C4 (Web Text))

Max Activating Token Index: 447

Text #11

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1824. Min Act: -0.0000

Data Index: 167156 (C4 (Web Text))

Max Activating Token Index: 591

Text #12

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1892. Min Act: -0.0001

Data Index: 1120527 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1691. Min Act: -0.0001

Data Index: 498124 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1816. Min Act: -0.0001

Data Index: 1218928 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1686. Min Act: -0.0001

Data Index: 1113864 (C4 (Web Text))

Max Activating Token Index: 140

Text #16

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1880. Min Act: -0.0001

Data Index: 393246 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1785. Min Act: -0.0001

Data Index: 119653 (C4 (Web Text))

Max Activating Token Index: 546

Text #18

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1774. Min Act: -0.0001

Data Index: 252807 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1766. Min Act: -0.0001

Data Index: 924441 (C4 (Web Text))

Max Activating Token Index: 841