Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 230 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5463. Min Range: -0.5463

Max Act: 0.5463. Min Act: -0.0002

Data Index: 205344 (C4 (Web Text))

Max Activating Token Index: 256

Text #1

Max Range: 0.5463. Min Range: -0.5463

Max Act: 0.5003. Min Act: -0.0003

Data Index: 93632 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 0.5463. Min Range: -0.5463

Max Act: 0.5149. Min Act: -0.0003

Data Index: 928872 (C4 (Web Text))

Max Activating Token Index: 170

Text #3

Max Range: 0.5463. Min Range: -0.5463

Max Act: 0.4447. Min Act: -0.0002

Data Index: 1333840 (C4 (Web Text))

Max Activating Token Index: 480

Text #4

Max Range: 0.5463. Min Range: -0.5463

Max Act: 0.4295. Min Act: -0.0002

Data Index: 803386 (C4 (Web Text))

Max Activating Token Index: 168

Text #5

Max Range: 0.5463. Min Range: -0.5463

Max Act: 0.4473. Min Act: -0.0002

Data Index: 361638 (C4 (Web Text))

Max Activating Token Index: 947

Text #6

Max Range: 0.5463. Min Range: -0.5463

Max Act: 0.4104. Min Act: -0.0002

Data Index: 540803 (C4 (Web Text))

Max Activating Token Index: 588

Text #7

Max Range: 0.5463. Min Range: -0.5463

Max Act: 0.4028. Min Act: -0.0003

Data Index: 348375 (C4 (Web Text))

Max Activating Token Index: 415

Text #8

Max Range: 0.5463. Min Range: -0.5463

Max Act: 0.4099. Min Act: -0.0002

Data Index: 1267051 (C4 (Web Text))

Max Activating Token Index: 486

Text #9

Max Range: 0.5463. Min Range: -0.5463

Max Act: 0.3972. Min Act: -0.0002

Data Index: 44210 (C4 (Web Text))

Max Activating Token Index: 418

Text #10

Max Range: 0.5463. Min Range: -0.5463

Max Act: 0.3907. Min Act: -0.0002

Data Index: 1091633 (C4 (Web Text))

Max Activating Token Index: 389

Text #11

Max Range: 0.5463. Min Range: -0.5463

Max Act: 0.3753. Min Act: -0.0002

Data Index: 1088532 (C4 (Web Text))

Max Activating Token Index: 748

Text #12

Max Range: 0.5463. Min Range: -0.5463

Max Act: 0.3640. Min Act: -0.0003

Data Index: 630458 (C4 (Web Text))

Max Activating Token Index: 50

Text #13

Max Range: 0.5463. Min Range: -0.5463

Max Act: 0.3665. Min Act: -0.0002

Data Index: 364677 (C4 (Web Text))

Max Activating Token Index: 331

Text #14

Max Range: 0.5463. Min Range: -0.5463

Max Act: 0.3542. Min Act: -0.0002

Data Index: 702231 (C4 (Web Text))

Max Activating Token Index: 794

Text #15

Max Range: 0.5463. Min Range: -0.5463

Max Act: 0.3624. Min Act: -0.0002

Data Index: 878461 (C4 (Web Text))

Max Activating Token Index: 860

Text #16

Max Range: 0.5463. Min Range: -0.5463

Max Act: 0.3606. Min Act: -0.0002

Data Index: 338106 (C4 (Web Text))

Max Activating Token Index: 442

Text #17

Max Range: 0.5463. Min Range: -0.5463

Max Act: 0.3590. Min Act: -0.0002

Data Index: 99443 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 0.5463. Min Range: -0.5463

Max Act: 0.3704. Min Act: -0.0002

Data Index: 755409 (C4 (Web Text))

Max Activating Token Index: 833

Text #19

Max Range: 0.5463. Min Range: -0.5463

Max Act: 0.3658. Min Act: -0.0003

Data Index: 750753 (C4 (Web Text))

Max Activating Token Index: 216