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

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

Neuron 2860 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7812. Min Range: -0.7812

Max Act: 0.7812. Min Act: -0.0001

Data Index: 795064 (C4 (Web Text))

Max Activating Token Index: 177

Text #1

Max Range: 0.7812. Min Range: -0.7812

Max Act: 0.7245. Min Act: -0.0001

Data Index: 10224 (C4 (Web Text))

Max Activating Token Index: 503

Text #2

Max Range: 0.7812. Min Range: -0.7812

Max Act: 0.6518. Min Act: -0.0001

Data Index: 853289 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 0.7812. Min Range: -0.7812

Max Act: 0.5840. Min Act: -0.0001

Data Index: 205160 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 0.7812. Min Range: -0.7812

Max Act: 0.5318. Min Act: -0.0001

Data Index: 113004 (C4 (Web Text))

Max Activating Token Index: 437

Text #5

Max Range: 0.7812. Min Range: -0.7812

Max Act: 0.5696. Min Act: -0.0001

Data Index: 399700 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 0.7812. Min Range: -0.7812

Max Act: 0.5660. Min Act: -0.0001

Data Index: 283875 (C4 (Web Text))

Max Activating Token Index: 931

Text #7

Max Range: 0.7812. Min Range: -0.7812

Max Act: 0.5618. Min Act: -0.0001

Data Index: 192233 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 0.7812. Min Range: -0.7812

Max Act: 0.5477. Min Act: -0.0001

Data Index: 162446 (C4 (Web Text))

Max Activating Token Index: 374

Text #9

Max Range: 0.7812. Min Range: -0.7812

Max Act: 0.5965. Min Act: -0.0001

Data Index: 253725 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 0.7812. Min Range: -0.7812

Max Act: 0.5749. Min Act: -0.0001

Data Index: 238328 (C4 (Web Text))

Max Activating Token Index: 467

Text #11

Max Range: 0.7812. Min Range: -0.7812

Max Act: 0.5489. Min Act: -0.0001

Data Index: 29745 (C4 (Web Text))

Max Activating Token Index: 392

Text #12

Max Range: 0.7812. Min Range: -0.7812

Max Act: 0.5290. Min Act: -0.0001

Data Index: 924592 (C4 (Web Text))

Max Activating Token Index: 465

Text #13

Max Range: 0.7812. Min Range: -0.7812

Max Act: 0.5062. Min Act: -0.0001

Data Index: 551829 (C4 (Web Text))

Max Activating Token Index: 621

Text #14

Max Range: 0.7812. Min Range: -0.7812

Max Act: 0.4972. Min Act: -0.0001

Data Index: 1355200 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 0.7812. Min Range: -0.7812

Max Act: 0.5395. Min Act: -0.0001

Data Index: 625770 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 0.7812. Min Range: -0.7812

Max Act: 0.5370. Min Act: -0.0001

Data Index: 1404096 (Python Code)

Max Activating Token Index: 481

Text #17

Max Range: 0.7812. Min Range: -0.7812

Max Act: 0.5525. Min Act: -0.0001

Data Index: 1029887 (C4 (Web Text))

Max Activating Token Index: 711

Text #18

Max Range: 0.7812. Min Range: -0.7812

Max Act: 0.4528. Min Act: -0.0001

Data Index: 798583 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 0.7812. Min Range: -0.7812

Max Act: 0.5106. Min Act: -0.0001

Data Index: 396730 (C4 (Web Text))

Max Activating Token Index: 474