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

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

Neuron 3294 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: 0.2422. Min Range: -0.2422

Max Act: 0.2422. Min Act: -0.0000

Data Index: 1281915 (C4 (Web Text))

Max Activating Token Index: 589

Text #1

Max Range: 0.2422. Min Range: -0.2422

Max Act: 0.2297. Min Act: -0.0000

Data Index: 122009 (C4 (Web Text))

Max Activating Token Index: 303

Text #2

Max Range: 0.2422. Min Range: -0.2422

Max Act: 0.2250. Min Act: -0.0000

Data Index: 539709 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 0.2422. Min Range: -0.2422

Max Act: 0.2096. Min Act: -0.0000

Data Index: 692143 (C4 (Web Text))

Max Activating Token Index: 249

Text #4

Max Range: 0.2422. Min Range: -0.2422

Max Act: 0.2150. Min Act: -0.0000

Data Index: 1189876 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 0.2422. Min Range: -0.2422

Max Act: 0.2042. Min Act: -0.0001

Data Index: 41955 (C4 (Web Text))

Max Activating Token Index: 226

Text #6

Max Range: 0.2422. Min Range: -0.2422

Max Act: 0.2005. Min Act: -0.0000

Data Index: 431823 (C4 (Web Text))

Max Activating Token Index: 622

Text #7

Max Range: 0.2422. Min Range: -0.2422

Max Act: 0.2015. Min Act: -0.0000

Data Index: 188938 (C4 (Web Text))

Max Activating Token Index: 785

Text #8

Max Range: 0.2422. Min Range: -0.2422

Max Act: 0.2000. Min Act: -0.0001

Data Index: 527242 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 0.2422. Min Range: -0.2422

Max Act: 0.1831. Min Act: -0.0001

Data Index: 1123845 (C4 (Web Text))

Max Activating Token Index: 886

Text #10

Max Range: 0.2422. Min Range: -0.2422

Max Act: 0.2096. Min Act: -0.0000

Data Index: 818855 (C4 (Web Text))

Max Activating Token Index: 298

Text #11

Max Range: 0.2422. Min Range: -0.2422

Max Act: 0.2089. Min Act: -0.0000

Data Index: 772798 (C4 (Web Text))

Max Activating Token Index: 126

Text #12

Max Range: 0.2422. Min Range: -0.2422

Max Act: 0.1945. Min Act: -0.0000

Data Index: 155903 (C4 (Web Text))

Max Activating Token Index: 128

Text #13

Max Range: 0.2422. Min Range: -0.2422

Max Act: 0.1932. Min Act: -0.0001

Data Index: 1135176 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 0.2422. Min Range: -0.2422

Max Act: 0.1932. Min Act: -0.0000

Data Index: 119240 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 0.2422. Min Range: -0.2422

Max Act: 0.1933. Min Act: -0.0001

Data Index: 994941 (C4 (Web Text))

Max Activating Token Index: 588

Text #16

Max Range: 0.2422. Min Range: -0.2422

Max Act: 0.1901. Min Act: -0.0000

Data Index: 813054 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 0.2422. Min Range: -0.2422

Max Act: 0.1943. Min Act: -0.0000

Data Index: 765719 (C4 (Web Text))

Max Activating Token Index: 346

Text #18

Max Range: 0.2422. Min Range: -0.2422

Max Act: 0.1853. Min Act: -0.0000

Data Index: 1350678 (C4 (Web Text))

Max Activating Token Index: 756

Text #19

Max Range: 0.2422. Min Range: -0.2422

Max Act: 0.1864. Min Act: -0.0000

Data Index: 1053739 (C4 (Web Text))

Max Activating Token Index: 119