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

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

Neuron 2852 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0990. Min Act: -0.0004

Data Index: 1322260 (C4 (Web Text))

Max Activating Token Index: 858

Text #1

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0859. Min Act: -0.0004

Data Index: 153548 (C4 (Web Text))

Max Activating Token Index: 580

Text #2

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0824. Min Act: -0.0004

Data Index: 145207 (C4 (Web Text))

Max Activating Token Index: 514

Text #3

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0792. Min Act: -0.0004

Data Index: 417022 (C4 (Web Text))

Max Activating Token Index: 278

Text #4

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0846. Min Act: -0.0004

Data Index: 621265 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0837. Min Act: -0.0004

Data Index: 869923 (C4 (Web Text))

Max Activating Token Index: 505

Text #6

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0833. Min Act: -0.0004

Data Index: 1022835 (C4 (Web Text))

Max Activating Token Index: 199

Text #7

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0840. Min Act: -0.0004

Data Index: 581080 (C4 (Web Text))

Max Activating Token Index: 742

Text #8

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0828. Min Act: -0.0004

Data Index: 1080724 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0825. Min Act: -0.0004

Data Index: 25990 (C4 (Web Text))

Max Activating Token Index: 672

Text #10

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0757. Min Act: -0.0004

Data Index: 774654 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0825. Min Act: -0.0004

Data Index: 1052841 (C4 (Web Text))

Max Activating Token Index: 454

Text #12

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0789. Min Act: -0.0004

Data Index: 870721 (C4 (Web Text))

Max Activating Token Index: 448

Text #13

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0818. Min Act: -0.0004

Data Index: 488212 (C4 (Web Text))

Max Activating Token Index: 938

Text #14

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0812. Min Act: -0.0004

Data Index: 1280636 (C4 (Web Text))

Max Activating Token Index: 439

Text #15

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0785. Min Act: -0.0004

Data Index: 445587 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0817. Min Act: -0.0004

Data Index: 1166925 (C4 (Web Text))

Max Activating Token Index: 922

Text #17

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0812. Min Act: -0.0004

Data Index: 53421 (C4 (Web Text))

Max Activating Token Index: 271

Text #18

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0767. Min Act: -0.0004

Data Index: 507500 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0773. Min Act: -0.0004

Data Index: 846876 (C4 (Web Text))

Max Activating Token Index: 686