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

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

Neuron 4447 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: 0.1482. Min Range: -0.1482

Max Act: 0.1482. Min Act: -0.0002

Data Index: 195633 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1242. Min Act: -0.0002

Data Index: 1252442 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.0982. Min Act: -0.0002

Data Index: 754106 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1114. Min Act: -0.0002

Data Index: 215942 (C4 (Web Text))

Max Activating Token Index: 314

Text #4

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.0997. Min Act: -0.0002

Data Index: 318125 (C4 (Web Text))

Max Activating Token Index: 779

Text #5

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1060. Min Act: -0.0002

Data Index: 529924 (C4 (Web Text))

Max Activating Token Index: 782

Text #6

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.0883. Min Act: -0.0002

Data Index: 627849 (C4 (Web Text))

Max Activating Token Index: 372

Text #7

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.0917. Min Act: -0.0002

Data Index: 684755 (C4 (Web Text))

Max Activating Token Index: 710

Text #8

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1012. Min Act: -0.0002

Data Index: 979244 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.0965. Min Act: -0.0002

Data Index: 77483 (C4 (Web Text))

Max Activating Token Index: 630

Text #10

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.0940. Min Act: -0.0002

Data Index: 206085 (C4 (Web Text))

Max Activating Token Index: 966

Text #11

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.0789. Min Act: -0.0002

Data Index: 116220 (C4 (Web Text))

Max Activating Token Index: 201

Text #12

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.0934. Min Act: -0.0002

Data Index: 849161 (C4 (Web Text))

Max Activating Token Index: 437

Text #13

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1008. Min Act: -0.0002

Data Index: 586022 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.0927. Min Act: -0.0002

Data Index: 854460 (C4 (Web Text))

Max Activating Token Index: 781

Text #15

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.0842. Min Act: -0.0002

Data Index: 252329 (C4 (Web Text))

Max Activating Token Index: 882

Text #16

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.0781. Min Act: -0.0002

Data Index: 969332 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.0910. Min Act: -0.0002

Data Index: 735212 (C4 (Web Text))

Max Activating Token Index: 580

Text #18

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.0840. Min Act: -0.0002

Data Index: 1343745 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.0902. Min Act: -0.0002

Data Index: 510365 (C4 (Web Text))

Max Activating Token Index: 769