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

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

Neuron 3758 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2128. Min Range: -0.2128

Max Act: 0.2106. Min Act: -0.0001

Data Index: 827731 (C4 (Web Text))

Max Activating Token Index: 607

Text #1

Max Range: 0.2128. Min Range: -0.2128

Max Act: 0.2128. Min Act: -0.0001

Data Index: 242901 (C4 (Web Text))

Max Activating Token Index: 236

Text #2

Max Range: 0.2128. Min Range: -0.2128

Max Act: 0.2048. Min Act: -0.0001

Data Index: 1026481 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 0.2128. Min Range: -0.2128

Max Act: 0.2050. Min Act: -0.0001

Data Index: 853426 (C4 (Web Text))

Max Activating Token Index: 676

Text #4

Max Range: 0.2128. Min Range: -0.2128

Max Act: 0.2091. Min Act: -0.0001

Data Index: 294932 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 0.2128. Min Range: -0.2128

Max Act: 0.2007. Min Act: -0.0001

Data Index: 966942 (C4 (Web Text))

Max Activating Token Index: 355

Text #6

Max Range: 0.2128. Min Range: -0.2128

Max Act: 0.1974. Min Act: -0.0001

Data Index: 924898 (C4 (Web Text))

Max Activating Token Index: 591

Text #7

Max Range: 0.2128. Min Range: -0.2128

Max Act: 0.1985. Min Act: -0.0001

Data Index: 486057 (C4 (Web Text))

Max Activating Token Index: 77

Text #8

Max Range: 0.2128. Min Range: -0.2128

Max Act: 0.1969. Min Act: -0.0001

Data Index: 536168 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 0.2128. Min Range: -0.2128

Max Act: 0.1893. Min Act: -0.0001

Data Index: 590963 (C4 (Web Text))

Max Activating Token Index: 692

Text #10

Max Range: 0.2128. Min Range: -0.2128

Max Act: 0.1819. Min Act: -0.0001

Data Index: 1587486 (Python Code)

Max Activating Token Index: 757

Text #11

Max Range: 0.2128. Min Range: -0.2128

Max Act: 0.1902. Min Act: -0.0001

Data Index: 327291 (C4 (Web Text))

Max Activating Token Index: 681

Text #12

Max Range: 0.2128. Min Range: -0.2128

Max Act: 0.1784. Min Act: -0.0001

Data Index: 706189 (C4 (Web Text))

Max Activating Token Index: 698

Text #13

Max Range: 0.2128. Min Range: -0.2128

Max Act: 0.1737. Min Act: -0.0001

Data Index: 58177 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 0.2128. Min Range: -0.2128

Max Act: 0.1867. Min Act: -0.0001

Data Index: 1005761 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 0.2128. Min Range: -0.2128

Max Act: 0.1838. Min Act: -0.0001

Data Index: 1194786 (C4 (Web Text))

Max Activating Token Index: 828

Text #16

Max Range: 0.2128. Min Range: -0.2128

Max Act: 0.1894. Min Act: -0.0001

Data Index: 530716 (C4 (Web Text))

Max Activating Token Index: 702

Text #17

Max Range: 0.2128. Min Range: -0.2128

Max Act: 0.1768. Min Act: -0.0001

Data Index: 512263 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 0.2128. Min Range: -0.2128

Max Act: 0.1890. Min Act: -0.0001

Data Index: 1180932 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 0.2128. Min Range: -0.2128

Max Act: 0.1824. Min Act: -0.0001

Data Index: 1263993 (C4 (Web Text))

Max Activating Token Index: 200