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

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

Neuron 3598 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0577. Min Range: -2.0577

Max Act: 1.9348. Min Act: -0.0000

Data Index: 1148617 (C4 (Web Text))

Max Activating Token Index: 582

Text #1

Max Range: 2.0577. Min Range: -2.0577

Max Act: 1.9219. Min Act: -0.0000

Data Index: 63059 (C4 (Web Text))

Max Activating Token Index: 372

Text #2

Max Range: 2.0577. Min Range: -2.0577

Max Act: 1.8861. Min Act: -0.0000

Data Index: 1045618 (C4 (Web Text))

Max Activating Token Index: 296

Text #3

Max Range: 2.0577. Min Range: -2.0577

Max Act: 2.0577. Min Act: -0.0000

Data Index: 214745 (C4 (Web Text))

Max Activating Token Index: 675

Text #4

Max Range: 2.0577. Min Range: -2.0577

Max Act: 1.9288. Min Act: -0.0000

Data Index: 137491 (C4 (Web Text))

Max Activating Token Index: 464

Text #5

Max Range: 2.0577. Min Range: -2.0577

Max Act: 1.8950. Min Act: -0.0000

Data Index: 327226 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 2.0577. Min Range: -2.0577

Max Act: 1.7259. Min Act: -0.0000

Data Index: 78025 (C4 (Web Text))

Max Activating Token Index: 970

Text #7

Max Range: 2.0577. Min Range: -2.0577

Max Act: 1.6826. Min Act: -0.0000

Data Index: 1306508 (C4 (Web Text))

Max Activating Token Index: 673

Text #8

Max Range: 2.0577. Min Range: -2.0577

Max Act: 1.8104. Min Act: -0.0000

Data Index: 200655 (C4 (Web Text))

Max Activating Token Index: 441

Text #9

Max Range: 2.0577. Min Range: -2.0577

Max Act: 1.8210. Min Act: -0.0000

Data Index: 136177 (C4 (Web Text))

Max Activating Token Index: 660

Text #10

Max Range: 2.0577. Min Range: -2.0577

Max Act: 1.7091. Min Act: -0.0000

Data Index: 73869 (C4 (Web Text))

Max Activating Token Index: 585

Text #11

Max Range: 2.0577. Min Range: -2.0577

Max Act: 1.6613. Min Act: -0.0000

Data Index: 557182 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 2.0577. Min Range: -2.0577

Max Act: 1.6870. Min Act: -0.0000

Data Index: 910749 (C4 (Web Text))

Max Activating Token Index: 228

Text #13

Max Range: 2.0577. Min Range: -2.0577

Max Act: 1.5425. Min Act: -0.0000

Data Index: 766643 (C4 (Web Text))

Max Activating Token Index: 416

Text #14

Max Range: 2.0577. Min Range: -2.0577

Max Act: 1.4305. Min Act: -0.0000

Data Index: 1308110 (C4 (Web Text))

Max Activating Token Index: 331

Text #15

Max Range: 2.0577. Min Range: -2.0577

Max Act: 1.4134. Min Act: -0.0000

Data Index: 492004 (C4 (Web Text))

Max Activating Token Index: 784

Text #16

Max Range: 2.0577. Min Range: -2.0577

Max Act: 1.5836. Min Act: -0.0000

Data Index: 118049 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 2.0577. Min Range: -2.0577

Max Act: 1.5123. Min Act: -0.0000

Data Index: 797114 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 2.0577. Min Range: -2.0577

Max Act: 1.6611. Min Act: -0.0000

Data Index: 450425 (C4 (Web Text))

Max Activating Token Index: 984

Text #19

Max Range: 2.0577. Min Range: -2.0577

Max Act: 1.4134. Min Act: -0.0000

Data Index: 986316 (C4 (Web Text))

Max Activating Token Index: 263