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

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

Neuron 2103 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0940. Min Act: -0.0001

Data Index: 417993 (C4 (Web Text))

Max Activating Token Index: 238

Text #1

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0893. Min Act: -0.0001

Data Index: 881922 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0739. Min Act: -0.0001

Data Index: 3189 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0805. Min Act: -0.0001

Data Index: 1362642 (Python Code)

Max Activating Token Index: 412

Text #4

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0674. Min Act: -0.0001

Data Index: 1486755 (Python Code)

Max Activating Token Index: 251

Text #5

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0829. Min Act: -0.0001

Data Index: 1516168 (Python Code)

Max Activating Token Index: 607

Text #6

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0761. Min Act: -0.0001

Data Index: 1015763 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0786. Min Act: -0.0001

Data Index: 940188 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0774. Min Act: -0.0001

Data Index: 1356629 (C4 (Web Text))

Max Activating Token Index: 1013

Text #9

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0802. Min Act: -0.0001

Data Index: 624619 (C4 (Web Text))

Max Activating Token Index: 804

Text #10

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0768. Min Act: -0.0001

Data Index: 1498422 (Python Code)

Max Activating Token Index: 506

Text #11

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0764. Min Act: -0.0001

Data Index: 1386036 (Python Code)

Max Activating Token Index: 731

Text #12

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0801. Min Act: -0.0001

Data Index: 598507 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0735. Min Act: -0.0001

Data Index: 1374914 (Python Code)

Max Activating Token Index: 138

Text #14

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0763. Min Act: -0.0001

Data Index: 1157766 (C4 (Web Text))

Max Activating Token Index: 137

Text #15

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0760. Min Act: -0.0001

Data Index: 445562 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0758. Min Act: -0.0001

Data Index: 902311 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0754. Min Act: -0.0001

Data Index: 392134 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0750. Min Act: -0.0000

Data Index: 770516 (C4 (Web Text))

Max Activating Token Index: 293

Text #19

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0716. Min Act: -0.0001

Data Index: 429958 (C4 (Web Text))

Max Activating Token Index: 204