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

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

Neuron 2734 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7590. Min Range: -4.7590

Max Act: 4.7590. Min Act: -0.0000

Data Index: 906825 (C4 (Web Text))

Max Activating Token Index: 154

Text #1

Max Range: 4.7590. Min Range: -4.7590

Max Act: 4.2383. Min Act: -0.0000

Data Index: 1098164 (C4 (Web Text))

Max Activating Token Index: 650

Text #2

Max Range: 4.7590. Min Range: -4.7590

Max Act: 4.0126. Min Act: -0.0000

Data Index: 319304 (C4 (Web Text))

Max Activating Token Index: 704

Text #3

Max Range: 4.7590. Min Range: -4.7590

Max Act: 3.7473. Min Act: -0.0000

Data Index: 886925 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 4.7590. Min Range: -4.7590

Max Act: 3.7011. Min Act: -0.0000

Data Index: 1255936 (C4 (Web Text))

Max Activating Token Index: 357

Text #5

Max Range: 4.7590. Min Range: -4.7590

Max Act: 3.4053. Min Act: -0.0000

Data Index: 1028944 (C4 (Web Text))

Max Activating Token Index: 87

Text #6

Max Range: 4.7590. Min Range: -4.7590

Max Act: 3.4966. Min Act: -0.0000

Data Index: 466064 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 4.7590. Min Range: -4.7590

Max Act: 3.3120. Min Act: -0.0000

Data Index: 33080 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 4.7590. Min Range: -4.7590

Max Act: 3.4755. Min Act: -0.0000

Data Index: 965052 (C4 (Web Text))

Max Activating Token Index: 837

Text #9

Max Range: 4.7590. Min Range: -4.7590

Max Act: 3.2438. Min Act: -0.0000

Data Index: 1285651 (C4 (Web Text))

Max Activating Token Index: 593

Text #10

Max Range: 4.7590. Min Range: -4.7590

Max Act: 3.5255. Min Act: -0.0000

Data Index: 858549 (C4 (Web Text))

Max Activating Token Index: 225

Text #11

Max Range: 4.7590. Min Range: -4.7590

Max Act: 3.3772. Min Act: -0.0000

Data Index: 416875 (C4 (Web Text))

Max Activating Token Index: 702

Text #12

Max Range: 4.7590. Min Range: -4.7590

Max Act: 3.6770. Min Act: -0.0000

Data Index: 1154468 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 4.7590. Min Range: -4.7590

Max Act: 3.3197. Min Act: -0.0000

Data Index: 1319552 (C4 (Web Text))

Max Activating Token Index: 666

Text #14

Max Range: 4.7590. Min Range: -4.7590

Max Act: 3.4723. Min Act: -0.0000

Data Index: 276554 (C4 (Web Text))

Max Activating Token Index: 381

Text #15

Max Range: 4.7590. Min Range: -4.7590

Max Act: 3.4478. Min Act: -0.0000

Data Index: 1244368 (C4 (Web Text))

Max Activating Token Index: 304

Text #16

Max Range: 4.7590. Min Range: -4.7590

Max Act: 3.3989. Min Act: -0.0000

Data Index: 549138 (C4 (Web Text))

Max Activating Token Index: 588

Text #17

Max Range: 4.7590. Min Range: -4.7590

Max Act: 3.2293. Min Act: -0.0000

Data Index: 1011961 (C4 (Web Text))

Max Activating Token Index: 434

Text #18

Max Range: 4.7590. Min Range: -4.7590

Max Act: 3.4891. Min Act: -0.0000

Data Index: 187883 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 4.7590. Min Range: -4.7590

Max Act: 3.4766. Min Act: -0.0000

Data Index: 650114 (C4 (Web Text))

Max Activating Token Index: 188