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

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

Neuron 1170 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4166. Min Range: -0.4166

Max Act: 0.4166. Min Act: -0.0000

Data Index: 1043122 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 0.4166. Min Range: -0.4166

Max Act: 0.3997. Min Act: -0.0000

Data Index: 227876 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 0.4166. Min Range: -0.4166

Max Act: 0.3787. Min Act: -0.0000

Data Index: 824644 (C4 (Web Text))

Max Activating Token Index: 577

Text #3

Max Range: 0.4166. Min Range: -0.4166

Max Act: 0.3770. Min Act: -0.0000

Data Index: 989489 (C4 (Web Text))

Max Activating Token Index: 254

Text #4

Max Range: 0.4166. Min Range: -0.4166

Max Act: 0.3268. Min Act: -0.0000

Data Index: 1281623 (C4 (Web Text))

Max Activating Token Index: 787

Text #5

Max Range: 0.4166. Min Range: -0.4166

Max Act: 0.3478. Min Act: -0.0000

Data Index: 1169874 (C4 (Web Text))

Max Activating Token Index: 707

Text #6

Max Range: 0.4166. Min Range: -0.4166

Max Act: 0.3276. Min Act: -0.0000

Data Index: 1090010 (C4 (Web Text))

Max Activating Token Index: 696

Text #7

Max Range: 0.4166. Min Range: -0.4166

Max Act: 0.3130. Min Act: -0.0000

Data Index: 898830 (C4 (Web Text))

Max Activating Token Index: 829

Text #8

Max Range: 0.4166. Min Range: -0.4166

Max Act: 0.3120. Min Act: -0.0000

Data Index: 11259 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 0.4166. Min Range: -0.4166

Max Act: 0.3306. Min Act: -0.0000

Data Index: 1017888 (C4 (Web Text))

Max Activating Token Index: 869

Text #10

Max Range: 0.4166. Min Range: -0.4166

Max Act: 0.3042. Min Act: -0.0000

Data Index: 1075885 (C4 (Web Text))

Max Activating Token Index: 260

Text #11

Max Range: 0.4166. Min Range: -0.4166

Max Act: 0.2930. Min Act: -0.0000

Data Index: 419008 (C4 (Web Text))

Max Activating Token Index: 272

Text #12

Max Range: 0.4166. Min Range: -0.4166

Max Act: 0.3130. Min Act: -0.0000

Data Index: 1283953 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 0.4166. Min Range: -0.4166

Max Act: 0.3098. Min Act: -0.0000

Data Index: 212563 (C4 (Web Text))

Max Activating Token Index: 994

Text #14

Max Range: 0.4166. Min Range: -0.4166

Max Act: 0.3035. Min Act: -0.0000

Data Index: 435448 (C4 (Web Text))

Max Activating Token Index: 908

Text #15

Max Range: 0.4166. Min Range: -0.4166

Max Act: 0.3037. Min Act: -0.0000

Data Index: 771840 (C4 (Web Text))

Max Activating Token Index: 986

Text #16

Max Range: 0.4166. Min Range: -0.4166

Max Act: 0.2914. Min Act: -0.0000

Data Index: 890323 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 0.4166. Min Range: -0.4166

Max Act: 0.3093. Min Act: -0.0000

Data Index: 68525 (C4 (Web Text))

Max Activating Token Index: 897

Text #18

Max Range: 0.4166. Min Range: -0.4166

Max Act: 0.3045. Min Act: -0.0000

Data Index: 1322484 (C4 (Web Text))

Max Activating Token Index: 110

Text #19

Max Range: 0.4166. Min Range: -0.4166

Max Act: 0.2927. Min Act: -0.0000

Data Index: 349302 (C4 (Web Text))

Max Activating Token Index: 993