Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 797 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.2342. Min Act: -0.0002

Data Index: 678775 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.2245. Min Act: -0.0002

Data Index: 609319 (C4 (Web Text))

Max Activating Token Index: 619

Text #2

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.2245. Min Act: -0.0002

Data Index: 999724 (C4 (Web Text))

Max Activating Token Index: 500

Text #3

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.2028. Min Act: -0.0002

Data Index: 1113405 (C4 (Web Text))

Max Activating Token Index: 472

Text #4

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.2059. Min Act: -0.0002

Data Index: 213805 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.2056. Min Act: -0.0002

Data Index: 1275563 (C4 (Web Text))

Max Activating Token Index: 230

Text #6

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.2262. Min Act: -0.0002

Data Index: 229087 (C4 (Web Text))

Max Activating Token Index: 649

Text #7

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1899. Min Act: -0.0002

Data Index: 1355500 (C4 (Web Text))

Max Activating Token Index: 745

Text #8

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.2002. Min Act: -0.0002

Data Index: 86885 (C4 (Web Text))

Max Activating Token Index: 202

Text #9

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.2120. Min Act: -0.0002

Data Index: 1042235 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.2065. Min Act: -0.0002

Data Index: 1350934 (C4 (Web Text))

Max Activating Token Index: 53

Text #11

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1912. Min Act: -0.0002

Data Index: 908391 (C4 (Web Text))

Max Activating Token Index: 241

Text #12

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1984. Min Act: -0.0002

Data Index: 508192 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1996. Min Act: -0.0002

Data Index: 119139 (C4 (Web Text))

Max Activating Token Index: 464

Text #14

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1962. Min Act: -0.0002

Data Index: 1344512 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1834. Min Act: -0.0002

Data Index: 512971 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1948. Min Act: -0.0002

Data Index: 980850 (C4 (Web Text))

Max Activating Token Index: 761

Text #17

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.2008. Min Act: -0.0002

Data Index: 254531 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1947. Min Act: -0.0002

Data Index: 128506 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1971. Min Act: -0.0002

Data Index: 419859 (C4 (Web Text))

Max Activating Token Index: 115