Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3414 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.6830. Min Act: -0.0000

Data Index: 682935 (C4 (Web Text))

Max Activating Token Index: 282

Text #1

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.6029. Min Act: -0.0000

Data Index: 830552 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.5243. Min Act: -0.0000

Data Index: 596491 (C4 (Web Text))

Max Activating Token Index: 835

Text #3

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.5132. Min Act: -0.0000

Data Index: 763311 (C4 (Web Text))

Max Activating Token Index: 556

Text #4

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.4882. Min Act: -0.0000

Data Index: 740195 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.5263. Min Act: -0.0000

Data Index: 608364 (C4 (Web Text))

Max Activating Token Index: 315

Text #6

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.5133. Min Act: -0.0000

Data Index: 14018 (C4 (Web Text))

Max Activating Token Index: 239

Text #7

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.4367. Min Act: -0.0000

Data Index: 1073316 (C4 (Web Text))

Max Activating Token Index: 719

Text #8

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.4735. Min Act: -0.0000

Data Index: 365517 (C4 (Web Text))

Max Activating Token Index: 187

Text #9

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.4629. Min Act: -0.0000

Data Index: 843574 (C4 (Web Text))

Max Activating Token Index: 948

Text #10

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.4590. Min Act: -0.0000

Data Index: 265373 (C4 (Web Text))

Max Activating Token Index: 100

Text #11

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.4741. Min Act: -0.0000

Data Index: 920425 (C4 (Web Text))

Max Activating Token Index: 846

Text #12

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.4118. Min Act: -0.0000

Data Index: 703512 (C4 (Web Text))

Max Activating Token Index: 359

Text #13

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.4532. Min Act: -0.0000

Data Index: 520610 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.4635. Min Act: -0.0000

Data Index: 838475 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.4924. Min Act: -0.0000

Data Index: 1032706 (C4 (Web Text))

Max Activating Token Index: 95

Text #16

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.4415. Min Act: -0.0000

Data Index: 1348734 (C4 (Web Text))

Max Activating Token Index: 710

Text #17

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.4752. Min Act: -0.0000

Data Index: 517956 (C4 (Web Text))

Max Activating Token Index: 734

Text #18

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.4452. Min Act: -0.0000

Data Index: 783846 (C4 (Web Text))

Max Activating Token Index: 488

Text #19

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.4708. Min Act: -0.0000

Data Index: 161289 (C4 (Web Text))

Max Activating Token Index: 839