Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 214 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.1091. Min Act: -0.0000

Data Index: 962148 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.1022. Min Act: -0.0001

Data Index: 268570 (C4 (Web Text))

Max Activating Token Index: 149

Text #2

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0950. Min Act: -0.0000

Data Index: 101133 (C4 (Web Text))

Max Activating Token Index: 573

Text #3

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0875. Min Act: -0.0000

Data Index: 1037925 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0933. Min Act: -0.0000

Data Index: 375970 (C4 (Web Text))

Max Activating Token Index: 980

Text #5

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0863. Min Act: -0.0001

Data Index: 1108964 (C4 (Web Text))

Max Activating Token Index: 427

Text #6

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0834. Min Act: -0.0000

Data Index: 26981 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0852. Min Act: -0.0001

Data Index: 1176464 (C4 (Web Text))

Max Activating Token Index: 680

Text #8

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0824. Min Act: -0.0000

Data Index: 746436 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0811. Min Act: -0.0000

Data Index: 118647 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0780. Min Act: -0.0000

Data Index: 656912 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0799. Min Act: -0.0001

Data Index: 704890 (C4 (Web Text))

Max Activating Token Index: 189

Text #12

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0803. Min Act: -0.0000

Data Index: 1169352 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0795. Min Act: -0.0000

Data Index: 396837 (C4 (Web Text))

Max Activating Token Index: 450

Text #14

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0795. Min Act: -0.0001

Data Index: 1147571 (C4 (Web Text))

Max Activating Token Index: 640

Text #15

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0780. Min Act: -0.0000

Data Index: 987095 (C4 (Web Text))

Max Activating Token Index: 473

Text #16

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0754. Min Act: -0.0000

Data Index: 1004235 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0771. Min Act: -0.0000

Data Index: 1044060 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0735. Min Act: -0.0000

Data Index: 153054 (C4 (Web Text))

Max Activating Token Index: 814

Text #19

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0763. Min Act: -0.0000

Data Index: 595138 (C4 (Web Text))

Max Activating Token Index: 510