Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.5786. Min Act: -0.0000

Data Index: 1005797 (C4 (Web Text))

Max Activating Token Index: 618

Text #1

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.6058. Min Act: -0.0000

Data Index: 52546 (C4 (Web Text))

Max Activating Token Index: 677

Text #2

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.5310. Min Act: -0.0000

Data Index: 1217311 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.5253. Min Act: -0.0000

Data Index: 296343 (C4 (Web Text))

Max Activating Token Index: 970

Text #4

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.5089. Min Act: -0.0000

Data Index: 769376 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.5080. Min Act: -0.0000

Data Index: 38049 (C4 (Web Text))

Max Activating Token Index: 356

Text #6

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4937. Min Act: -0.0000

Data Index: 891082 (C4 (Web Text))

Max Activating Token Index: 695

Text #7

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.5028. Min Act: -0.0000

Data Index: 881992 (C4 (Web Text))

Max Activating Token Index: 624

Text #8

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.5003. Min Act: -0.0000

Data Index: 878061 (C4 (Web Text))

Max Activating Token Index: 938

Text #9

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.5052. Min Act: -0.0000

Data Index: 830992 (C4 (Web Text))

Max Activating Token Index: 614

Text #10

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.5546. Min Act: -0.0000

Data Index: 745509 (C4 (Web Text))

Max Activating Token Index: 643

Text #11

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.5163. Min Act: -0.0000

Data Index: 424238 (C4 (Web Text))

Max Activating Token Index: 629

Text #12

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4987. Min Act: -0.0000

Data Index: 767902 (C4 (Web Text))

Max Activating Token Index: 148

Text #13

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4976. Min Act: -0.0000

Data Index: 1018391 (C4 (Web Text))

Max Activating Token Index: 998

Text #14

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4793. Min Act: -0.0000

Data Index: 1011725 (C4 (Web Text))

Max Activating Token Index: 605

Text #15

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4931. Min Act: -0.0000

Data Index: 469057 (C4 (Web Text))

Max Activating Token Index: 662

Text #16

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4917. Min Act: -0.0000

Data Index: 56460 (C4 (Web Text))

Max Activating Token Index: 820

Text #17

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4920. Min Act: -0.0000

Data Index: 955251 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4864. Min Act: -0.0000

Data Index: 627949 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4718. Min Act: -0.0000

Data Index: 338640 (C4 (Web Text))

Max Activating Token Index: 550