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

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

Neuron 3246 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.2048. Min Act: -0.0000

Data Index: 1357261 (C4 (Web Text))

Max Activating Token Index: 721

Text #1

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1984. Min Act: -0.0000

Data Index: 413447 (C4 (Web Text))

Max Activating Token Index: 819

Text #2

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.2051. Min Act: -0.0000

Data Index: 112681 (C4 (Web Text))

Max Activating Token Index: 927

Text #3

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.2101. Min Act: -0.0000

Data Index: 420324 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1943. Min Act: -0.0001

Data Index: 19778 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1866. Min Act: -0.0000

Data Index: 251307 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1915. Min Act: -0.0000

Data Index: 944321 (C4 (Web Text))

Max Activating Token Index: 982

Text #7

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1849. Min Act: -0.0000

Data Index: 220236 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1862. Min Act: -0.0000

Data Index: 1233975 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1815. Min Act: -0.0000

Data Index: 1215821 (C4 (Web Text))

Max Activating Token Index: 571

Text #10

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1872. Min Act: -0.0000

Data Index: 1291781 (C4 (Web Text))

Max Activating Token Index: 922

Text #11

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1742. Min Act: -0.0000

Data Index: 80718 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1801. Min Act: -0.0000

Data Index: 900163 (C4 (Web Text))

Max Activating Token Index: 350

Text #13

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1776. Min Act: -0.0000

Data Index: 1272038 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1823. Min Act: -0.0000

Data Index: 1126309 (C4 (Web Text))

Max Activating Token Index: 763

Text #15

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1723. Min Act: -0.0000

Data Index: 1025312 (C4 (Web Text))

Max Activating Token Index: 890

Text #16

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1692. Min Act: -0.0000

Data Index: 281657 (C4 (Web Text))

Max Activating Token Index: 913

Text #17

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1648. Min Act: -0.0000

Data Index: 1197684 (C4 (Web Text))

Max Activating Token Index: 769

Text #18

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1808. Min Act: -0.0000

Data Index: 557952 (C4 (Web Text))

Max Activating Token Index: 457

Text #19

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1521. Min Act: -0.0000

Data Index: 808014 (C4 (Web Text))

Max Activating Token Index: 524