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

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

Neuron 326 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: 0.2434. Min Range: -0.2434

Max Act: 0.2400. Min Act: -0.0002

Data Index: 484376 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 0.2434. Min Range: -0.2434

Max Act: 0.2434. Min Act: -0.0003

Data Index: 168839 (C4 (Web Text))

Max Activating Token Index: 858

Text #2

Max Range: 0.2434. Min Range: -0.2434

Max Act: 0.2020. Min Act: -0.0002

Data Index: 893302 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 0.2434. Min Range: -0.2434

Max Act: 0.2103. Min Act: -0.0002

Data Index: 628687 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 0.2434. Min Range: -0.2434

Max Act: 0.2070. Min Act: -0.0002

Data Index: 1069487 (C4 (Web Text))

Max Activating Token Index: 793

Text #5

Max Range: 0.2434. Min Range: -0.2434

Max Act: 0.2031. Min Act: -0.0002

Data Index: 505525 (C4 (Web Text))

Max Activating Token Index: 753

Text #6

Max Range: 0.2434. Min Range: -0.2434

Max Act: 0.2035. Min Act: -0.0002

Data Index: 951916 (C4 (Web Text))

Max Activating Token Index: 483

Text #7

Max Range: 0.2434. Min Range: -0.2434

Max Act: 0.2024. Min Act: -0.0002

Data Index: 7943 (C4 (Web Text))

Max Activating Token Index: 81

Text #8

Max Range: 0.2434. Min Range: -0.2434

Max Act: 0.2073. Min Act: -0.0002

Data Index: 1120717 (C4 (Web Text))

Max Activating Token Index: 943

Text #9

Max Range: 0.2434. Min Range: -0.2434

Max Act: 0.2081. Min Act: -0.0002

Data Index: 881756 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 0.2434. Min Range: -0.2434

Max Act: 0.2049. Min Act: -0.0002

Data Index: 817176 (C4 (Web Text))

Max Activating Token Index: 981

Text #11

Max Range: 0.2434. Min Range: -0.2434

Max Act: 0.1958. Min Act: -0.0002

Data Index: 267446 (C4 (Web Text))

Max Activating Token Index: 566

Text #12

Max Range: 0.2434. Min Range: -0.2434

Max Act: 0.1879. Min Act: -0.0002

Data Index: 232565 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 0.2434. Min Range: -0.2434

Max Act: 0.1964. Min Act: -0.0002

Data Index: 998044 (C4 (Web Text))

Max Activating Token Index: 488

Text #14

Max Range: 0.2434. Min Range: -0.2434

Max Act: 0.2097. Min Act: -0.0002

Data Index: 1224058 (C4 (Web Text))

Max Activating Token Index: 743

Text #15

Max Range: 0.2434. Min Range: -0.2434

Max Act: 0.2205. Min Act: -0.0002

Data Index: 1080993 (C4 (Web Text))

Max Activating Token Index: 702

Text #16

Max Range: 0.2434. Min Range: -0.2434

Max Act: 0.1973. Min Act: -0.0002

Data Index: 70903 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 0.2434. Min Range: -0.2434

Max Act: 0.1858. Min Act: -0.0002

Data Index: 211011 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 0.2434. Min Range: -0.2434

Max Act: 0.1916. Min Act: -0.0002

Data Index: 87976 (C4 (Web Text))

Max Activating Token Index: 833

Text #19

Max Range: 0.2434. Min Range: -0.2434

Max Act: 0.1941. Min Act: -0.0002

Data Index: 838822 (C4 (Web Text))

Max Activating Token Index: 806