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

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

Neuron 1889 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.1064. Min Act: -0.0000

Data Index: 886511 (C4 (Web Text))

Max Activating Token Index: 674

Text #1

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0946. Min Act: -0.0000

Data Index: 1118366 (C4 (Web Text))

Max Activating Token Index: 974

Text #2

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0968. Min Act: -0.0001

Data Index: 1200275 (C4 (Web Text))

Max Activating Token Index: 265

Text #3

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0902. Min Act: -0.0000

Data Index: 916078 (C4 (Web Text))

Max Activating Token Index: 925

Text #4

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0790. Min Act: -0.0000

Data Index: 954770 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0771. Min Act: -0.0000

Data Index: 285817 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0693. Min Act: -0.0000

Data Index: 1233574 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0710. Min Act: -0.0000

Data Index: 1334446 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0588. Min Act: -0.0000

Data Index: 794147 (C4 (Web Text))

Max Activating Token Index: 233

Text #9

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0692. Min Act: -0.0000

Data Index: 1222868 (C4 (Web Text))

Max Activating Token Index: 927

Text #10

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0707. Min Act: -0.0000

Data Index: 218983 (C4 (Web Text))

Max Activating Token Index: 355

Text #11

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0760. Min Act: -0.0001

Data Index: 704044 (C4 (Web Text))

Max Activating Token Index: 732

Text #12

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0682. Min Act: -0.0000

Data Index: 1267238 (C4 (Web Text))

Max Activating Token Index: 747

Text #13

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0659. Min Act: -0.0000

Data Index: 458449 (C4 (Web Text))

Max Activating Token Index: 753

Text #14

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0666. Min Act: -0.0000

Data Index: 739683 (C4 (Web Text))

Max Activating Token Index: 39

Text #15

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0605. Min Act: -0.0000

Data Index: 1249486 (C4 (Web Text))

Max Activating Token Index: 730

Text #16

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0612. Min Act: -0.0000

Data Index: 225366 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0709. Min Act: -0.0000

Data Index: 346788 (C4 (Web Text))

Max Activating Token Index: 777

Text #18

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0595. Min Act: -0.0001

Data Index: 1423966 (Python Code)

Max Activating Token Index: 518

Text #19

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0664. Min Act: -0.0000

Data Index: 373322 (C4 (Web Text))

Max Activating Token Index: 756