Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1782 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0433. Min Act: -0.0005

Data Index: 415545 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0430. Min Act: -0.0005

Data Index: 422027 (C4 (Web Text))

Max Activating Token Index: 337

Text #2

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0423. Min Act: -0.0005

Data Index: 143816 (C4 (Web Text))

Max Activating Token Index: 783

Text #3

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0410. Min Act: -0.0005

Data Index: 939316 (C4 (Web Text))

Max Activating Token Index: 308

Text #4

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0408. Min Act: -0.0005

Data Index: 940400 (C4 (Web Text))

Max Activating Token Index: 904

Text #5

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0392. Min Act: -0.0005

Data Index: 196685 (C4 (Web Text))

Max Activating Token Index: 219

Text #6

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0396. Min Act: -0.0005

Data Index: 668906 (C4 (Web Text))

Max Activating Token Index: 125

Text #7

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0387. Min Act: -0.0005

Data Index: 108572 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0393. Min Act: -0.0005

Data Index: 858702 (C4 (Web Text))

Max Activating Token Index: 845

Text #9

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0394. Min Act: -0.0005

Data Index: 546124 (C4 (Web Text))

Max Activating Token Index: 95

Text #10

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0393. Min Act: -0.0005

Data Index: 821072 (C4 (Web Text))

Max Activating Token Index: 477

Text #11

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0389. Min Act: -0.0005

Data Index: 509797 (C4 (Web Text))

Max Activating Token Index: 758

Text #12

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0381. Min Act: -0.0005

Data Index: 684678 (C4 (Web Text))

Max Activating Token Index: 903

Text #13

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0394. Min Act: -0.0005

Data Index: 734811 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0411. Min Act: -0.0005

Data Index: 106040 (C4 (Web Text))

Max Activating Token Index: 848

Text #15

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0374. Min Act: -0.0005

Data Index: 1264195 (C4 (Web Text))

Max Activating Token Index: 282

Text #16

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0384. Min Act: -0.0005

Data Index: 527887 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0381. Min Act: -0.0005

Data Index: 1308735 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0379. Min Act: -0.0005

Data Index: 227966 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0380. Min Act: -0.0005

Data Index: 258105 (C4 (Web Text))

Max Activating Token Index: 903