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

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

Neuron 1880 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.4090. Min Act: -0.0003

Data Index: 1215610 (C4 (Web Text))

Max Activating Token Index: 245

Text #1

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3910. Min Act: -0.0003

Data Index: 58416 (C4 (Web Text))

Max Activating Token Index: 664

Text #2

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3789. Min Act: -0.0003

Data Index: 20964 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3499. Min Act: -0.0003

Data Index: 908112 (C4 (Web Text))

Max Activating Token Index: 765

Text #4

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3695. Min Act: -0.0003

Data Index: 747803 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3098. Min Act: -0.0003

Data Index: 1171718 (C4 (Web Text))

Max Activating Token Index: 529

Text #6

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3411. Min Act: -0.0003

Data Index: 1273851 (C4 (Web Text))

Max Activating Token Index: 663

Text #7

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3206. Min Act: -0.0003

Data Index: 419591 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3156. Min Act: -0.0002

Data Index: 1053509 (C4 (Web Text))

Max Activating Token Index: 744

Text #9

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3155. Min Act: -0.0003

Data Index: 1183378 (C4 (Web Text))

Max Activating Token Index: 398

Text #10

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3068. Min Act: -0.0003

Data Index: 440252 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3036. Min Act: -0.0003

Data Index: 10924 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3012. Min Act: -0.0003

Data Index: 1067749 (C4 (Web Text))

Max Activating Token Index: 156

Text #13

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.2988. Min Act: -0.0002

Data Index: 1119301 (C4 (Web Text))

Max Activating Token Index: 841

Text #14

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.2982. Min Act: -0.0003

Data Index: 555603 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.2958. Min Act: -0.0003

Data Index: 859521 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.2959. Min Act: -0.0003

Data Index: 645899 (C4 (Web Text))

Max Activating Token Index: 664

Text #17

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.2933. Min Act: -0.0003

Data Index: 648816 (C4 (Web Text))

Max Activating Token Index: 386

Text #18

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.2926. Min Act: -0.0002

Data Index: 28533 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.2914. Min Act: -0.0003

Data Index: 384615 (C4 (Web Text))

Max Activating Token Index: 338