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

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

Neuron 2007 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: 0.0934. Min Range: -0.0934

Max Act: 0.0934. Min Act: -0.0004

Data Index: 1550225 (Python Code)

Max Activating Token Index: 544

Text #1

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0924. Min Act: -0.0004

Data Index: 127459 (C4 (Web Text))

Max Activating Token Index: 835

Text #2

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0841. Min Act: -0.0004

Data Index: 77487 (C4 (Web Text))

Max Activating Token Index: 253

Text #3

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0911. Min Act: -0.0004

Data Index: 181529 (C4 (Web Text))

Max Activating Token Index: 273

Text #4

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0853. Min Act: -0.0004

Data Index: 920640 (C4 (Web Text))

Max Activating Token Index: 534

Text #5

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0881. Min Act: -0.0004

Data Index: 1438092 (Python Code)

Max Activating Token Index: 264

Text #6

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0874. Min Act: -0.0004

Data Index: 900247 (C4 (Web Text))

Max Activating Token Index: 95

Text #7

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0831. Min Act: -0.0004

Data Index: 1478755 (Python Code)

Max Activating Token Index: 882

Text #8

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0848. Min Act: -0.0004

Data Index: 1057468 (C4 (Web Text))

Max Activating Token Index: 17

Text #9

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0845. Min Act: -0.0004

Data Index: 70556 (C4 (Web Text))

Max Activating Token Index: 359

Text #10

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0798. Min Act: -0.0004

Data Index: 451366 (C4 (Web Text))

Max Activating Token Index: 819

Text #11

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0792. Min Act: -0.0004

Data Index: 32245 (C4 (Web Text))

Max Activating Token Index: 995

Text #12

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0738. Min Act: -0.0004

Data Index: 563679 (C4 (Web Text))

Max Activating Token Index: 930

Text #13

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0742. Min Act: -0.0004

Data Index: 1379235 (Python Code)

Max Activating Token Index: 466

Text #14

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0655. Min Act: -0.0004

Data Index: 1430678 (Python Code)

Max Activating Token Index: 794

Text #15

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0706. Min Act: -0.0004

Data Index: 349347 (C4 (Web Text))

Max Activating Token Index: 289

Text #16

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0702. Min Act: -0.0004

Data Index: 574551 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0691. Min Act: -0.0004

Data Index: 311441 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0746. Min Act: -0.0004

Data Index: 787269 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0718. Min Act: -0.0004

Data Index: 380750 (C4 (Web Text))

Max Activating Token Index: 755