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

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

Neuron 2951 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2675. Min Range: -4.2675

Max Act: 4.2675. Min Act: -0.0000

Data Index: 13233 (C4 (Web Text))

Max Activating Token Index: 243

Text #1

Max Range: 4.2675. Min Range: -4.2675

Max Act: 3.3974. Min Act: -0.0000

Data Index: 617273 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 4.2675. Min Range: -4.2675

Max Act: 3.2716. Min Act: -0.0000

Data Index: 1252895 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 4.2675. Min Range: -4.2675

Max Act: 2.9938. Min Act: -0.0000

Data Index: 914360 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 4.2675. Min Range: -4.2675

Max Act: 2.9204. Min Act: -0.0000

Data Index: 635231 (C4 (Web Text))

Max Activating Token Index: 783

Text #5

Max Range: 4.2675. Min Range: -4.2675

Max Act: 2.9985. Min Act: -0.0000

Data Index: 275349 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 4.2675. Min Range: -4.2675

Max Act: 2.7969. Min Act: -0.0000

Data Index: 57775 (C4 (Web Text))

Max Activating Token Index: 194

Text #7

Max Range: 4.2675. Min Range: -4.2675

Max Act: 2.6176. Min Act: -0.0000

Data Index: 844495 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 4.2675. Min Range: -4.2675

Max Act: 2.5574. Min Act: -0.0000

Data Index: 548067 (C4 (Web Text))

Max Activating Token Index: 479

Text #9

Max Range: 4.2675. Min Range: -4.2675

Max Act: 2.5525. Min Act: -0.0000

Data Index: 207014 (C4 (Web Text))

Max Activating Token Index: 962

Text #10

Max Range: 4.2675. Min Range: -4.2675

Max Act: 2.5068. Min Act: -0.0000

Data Index: 1112465 (C4 (Web Text))

Max Activating Token Index: 3

Text #11

Max Range: 4.2675. Min Range: -4.2675

Max Act: 2.6305. Min Act: -0.0000

Data Index: 626814 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 4.2675. Min Range: -4.2675

Max Act: 2.6214. Min Act: -0.0000

Data Index: 936900 (C4 (Web Text))

Max Activating Token Index: 595

Text #13

Max Range: 4.2675. Min Range: -4.2675

Max Act: 2.6217. Min Act: -0.0000

Data Index: 567974 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 4.2675. Min Range: -4.2675

Max Act: 2.4663. Min Act: -0.0000

Data Index: 287748 (C4 (Web Text))

Max Activating Token Index: 670

Text #15

Max Range: 4.2675. Min Range: -4.2675

Max Act: 2.4423. Min Act: -0.0000

Data Index: 1388887 (Python Code)

Max Activating Token Index: 235

Text #16

Max Range: 4.2675. Min Range: -4.2675

Max Act: 2.5897. Min Act: -0.0000

Data Index: 91499 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 4.2675. Min Range: -4.2675

Max Act: 2.5674. Min Act: -0.0000

Data Index: 497581 (C4 (Web Text))

Max Activating Token Index: 567

Text #18

Max Range: 4.2675. Min Range: -4.2675

Max Act: 2.6988. Min Act: -0.0000

Data Index: 883873 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 4.2675. Min Range: -4.2675

Max Act: 2.5480. Min Act: -0.0000

Data Index: 85607 (C4 (Web Text))

Max Activating Token Index: 598