Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 716 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0098. Min Act: -0.0004

Data Index: 57652 (C4 (Web Text))

Max Activating Token Index: 737

Text #1

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0095. Min Act: -0.0003

Data Index: 755918 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0095. Min Act: -0.0003

Data Index: 256875 (C4 (Web Text))

Max Activating Token Index: 289

Text #3

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0093. Min Act: -0.0003

Data Index: 366670 (C4 (Web Text))

Max Activating Token Index: 649

Text #4

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0093. Min Act: -0.0003

Data Index: 1101202 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0090. Min Act: -0.0003

Data Index: 1279613 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0090. Min Act: -0.0003

Data Index: 201593 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0090. Min Act: -0.0004

Data Index: 15241 (C4 (Web Text))

Max Activating Token Index: 393

Text #8

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0091. Min Act: -0.0003

Data Index: 1293159 (C4 (Web Text))

Max Activating Token Index: 499

Text #9

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0088. Min Act: -0.0004

Data Index: 1298592 (C4 (Web Text))

Max Activating Token Index: 692

Text #10

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0089. Min Act: -0.0003

Data Index: 693410 (C4 (Web Text))

Max Activating Token Index: 512

Text #11

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0088. Min Act: -0.0004

Data Index: 871288 (C4 (Web Text))

Max Activating Token Index: 626

Text #12

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0088. Min Act: -0.0003

Data Index: 1169011 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0088. Min Act: -0.0003

Data Index: 361855 (C4 (Web Text))

Max Activating Token Index: 811

Text #14

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0088. Min Act: -0.0004

Data Index: 686012 (C4 (Web Text))

Max Activating Token Index: 541

Text #15

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0088. Min Act: -0.0004

Data Index: 943847 (C4 (Web Text))

Max Activating Token Index: 725

Text #16

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0088. Min Act: -0.0004

Data Index: 691629 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0088. Min Act: -0.0003

Data Index: 1280560 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0088. Min Act: -0.0004

Data Index: 1238736 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0088. Min Act: -0.0003

Data Index: 16191 (C4 (Web Text))

Max Activating Token Index: 551