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

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

Neuron 1481 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2384. Min Act: -0.0002

Data Index: 1083681 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2227. Min Act: -0.0002

Data Index: 363114 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2049. Min Act: -0.0002

Data Index: 120871 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2179. Min Act: -0.0002

Data Index: 166467 (C4 (Web Text))

Max Activating Token Index: 924

Text #4

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2245. Min Act: -0.0002

Data Index: 1343098 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2211. Min Act: -0.0002

Data Index: 748549 (C4 (Web Text))

Max Activating Token Index: 875

Text #6

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2103. Min Act: -0.0001

Data Index: 316798 (C4 (Web Text))

Max Activating Token Index: 283

Text #7

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2019. Min Act: -0.0001

Data Index: 582822 (C4 (Web Text))

Max Activating Token Index: 1004

Text #8

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2145. Min Act: -0.0001

Data Index: 951732 (C4 (Web Text))

Max Activating Token Index: 471

Text #9

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2031. Min Act: -0.0001

Data Index: 274564 (C4 (Web Text))

Max Activating Token Index: 878

Text #10

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2003. Min Act: -0.0002

Data Index: 800073 (C4 (Web Text))

Max Activating Token Index: 692

Text #11

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2078. Min Act: -0.0002

Data Index: 759970 (C4 (Web Text))

Max Activating Token Index: 668

Text #12

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2023. Min Act: -0.0002

Data Index: 515551 (C4 (Web Text))

Max Activating Token Index: 25

Text #13

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2070. Min Act: -0.0002

Data Index: 1199794 (C4 (Web Text))

Max Activating Token Index: 67

Text #14

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2199. Min Act: -0.0002

Data Index: 1210280 (C4 (Web Text))

Max Activating Token Index: 962

Text #15

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1852. Min Act: -0.0002

Data Index: 341128 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1904. Min Act: -0.0002

Data Index: 660750 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1966. Min Act: -0.0002

Data Index: 871453 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2035. Min Act: -0.0001

Data Index: 304448 (C4 (Web Text))

Max Activating Token Index: 584

Text #19

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1893. Min Act: -0.0002

Data Index: 836771 (C4 (Web Text))

Max Activating Token Index: 10