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

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

Neuron 5214 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0913. Min Act: -0.0001

Data Index: 751692 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0878. Min Act: -0.0001

Data Index: 131713 (C4 (Web Text))

Max Activating Token Index: 231

Text #2

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0848. Min Act: -0.0001

Data Index: 435900 (C4 (Web Text))

Max Activating Token Index: 667

Text #3

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0877. Min Act: -0.0001

Data Index: 1339977 (C4 (Web Text))

Max Activating Token Index: 502

Text #4

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0836. Min Act: -0.0001

Data Index: 266417 (C4 (Web Text))

Max Activating Token Index: 999

Text #5

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0790. Min Act: -0.0001

Data Index: 634318 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0820. Min Act: -0.0001

Data Index: 365872 (C4 (Web Text))

Max Activating Token Index: 472

Text #7

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0816. Min Act: -0.0001

Data Index: 702546 (C4 (Web Text))

Max Activating Token Index: 576

Text #8

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0780. Min Act: -0.0001

Data Index: 1147318 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0783. Min Act: -0.0001

Data Index: 1503268 (Python Code)

Max Activating Token Index: 697

Text #10

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0771. Min Act: -0.0001

Data Index: 802459 (C4 (Web Text))

Max Activating Token Index: 549

Text #11

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0732. Min Act: -0.0001

Data Index: 1004819 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0755. Min Act: -0.0001

Data Index: 1097182 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0756. Min Act: -0.0001

Data Index: 1258192 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0744. Min Act: -0.0001

Data Index: 262851 (C4 (Web Text))

Max Activating Token Index: 622

Text #15

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0757. Min Act: -0.0001

Data Index: 1490712 (Python Code)

Max Activating Token Index: 536

Text #16

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0769. Min Act: -0.0001

Data Index: 64117 (C4 (Web Text))

Max Activating Token Index: 366

Text #17

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0658. Min Act: -0.0001

Data Index: 1269706 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0707. Min Act: -0.0001

Data Index: 472719 (C4 (Web Text))

Max Activating Token Index: 550

Text #19

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0725. Min Act: -0.0001

Data Index: 1049542 (C4 (Web Text))

Max Activating Token Index: 691