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

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

Neuron 3867 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0919. Min Range: -4.0919

Max Act: 4.0919. Min Act: -0.0000

Data Index: 1094832 (C4 (Web Text))

Max Activating Token Index: 419

Text #1

Max Range: 4.0919. Min Range: -4.0919

Max Act: 3.4978. Min Act: -0.0000

Data Index: 199631 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 4.0919. Min Range: -4.0919

Max Act: 3.5243. Min Act: -0.0000

Data Index: 592179 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 4.0919. Min Range: -4.0919

Max Act: 3.5052. Min Act: -0.0000

Data Index: 815260 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 4.0919. Min Range: -4.0919

Max Act: 3.3021. Min Act: -0.0000

Data Index: 1064427 (C4 (Web Text))

Max Activating Token Index: 594

Text #5

Max Range: 4.0919. Min Range: -4.0919

Max Act: 3.3907. Min Act: -0.0000

Data Index: 498108 (C4 (Web Text))

Max Activating Token Index: 366

Text #6

Max Range: 4.0919. Min Range: -4.0919

Max Act: 3.2016. Min Act: -0.0000

Data Index: 719482 (C4 (Web Text))

Max Activating Token Index: 153

Text #7

Max Range: 4.0919. Min Range: -4.0919

Max Act: 3.2013. Min Act: -0.0000

Data Index: 163576 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 4.0919. Min Range: -4.0919

Max Act: 3.1845. Min Act: -0.0000

Data Index: 5068 (C4 (Web Text))

Max Activating Token Index: 529

Text #9

Max Range: 4.0919. Min Range: -4.0919

Max Act: 3.0915. Min Act: -0.0000

Data Index: 2953 (C4 (Web Text))

Max Activating Token Index: 341

Text #10

Max Range: 4.0919. Min Range: -4.0919

Max Act: 2.9274. Min Act: -0.0000

Data Index: 396883 (C4 (Web Text))

Max Activating Token Index: 399

Text #11

Max Range: 4.0919. Min Range: -4.0919

Max Act: 3.2257. Min Act: -0.0000

Data Index: 68406 (C4 (Web Text))

Max Activating Token Index: 396

Text #12

Max Range: 4.0919. Min Range: -4.0919

Max Act: 3.0383. Min Act: -0.0000

Data Index: 953638 (C4 (Web Text))

Max Activating Token Index: 67

Text #13

Max Range: 4.0919. Min Range: -4.0919

Max Act: 3.0459. Min Act: -0.0000

Data Index: 1195195 (C4 (Web Text))

Max Activating Token Index: 933

Text #14

Max Range: 4.0919. Min Range: -4.0919

Max Act: 3.1299. Min Act: -0.0000

Data Index: 578066 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 4.0919. Min Range: -4.0919

Max Act: 3.1126. Min Act: -0.0000

Data Index: 681203 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 4.0919. Min Range: -4.0919

Max Act: 2.9472. Min Act: -0.0000

Data Index: 777132 (C4 (Web Text))

Max Activating Token Index: 472

Text #17

Max Range: 4.0919. Min Range: -4.0919

Max Act: 3.0577. Min Act: -0.0000

Data Index: 1001906 (C4 (Web Text))

Max Activating Token Index: 427

Text #18

Max Range: 4.0919. Min Range: -4.0919

Max Act: 3.0767. Min Act: -0.0000

Data Index: 918952 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 4.0919. Min Range: -4.0919

Max Act: 2.9312. Min Act: -0.0000

Data Index: 133297 (C4 (Web Text))

Max Activating Token Index: 149