Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2720 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0903. Min Act: -0.0003

Data Index: 445923 (C4 (Web Text))

Max Activating Token Index: 543

Text #1

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0898. Min Act: -0.0003

Data Index: 176739 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0891. Min Act: -0.0003

Data Index: 269968 (C4 (Web Text))

Max Activating Token Index: 488

Text #3

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0848. Min Act: -0.0003

Data Index: 1142086 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0892. Min Act: -0.0003

Data Index: 1215230 (C4 (Web Text))

Max Activating Token Index: 980

Text #5

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0816. Min Act: -0.0003

Data Index: 1127816 (C4 (Web Text))

Max Activating Token Index: 374

Text #6

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0809. Min Act: -0.0003

Data Index: 171044 (C4 (Web Text))

Max Activating Token Index: 526

Text #7

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0819. Min Act: -0.0003

Data Index: 713650 (C4 (Web Text))

Max Activating Token Index: 657

Text #8

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0829. Min Act: -0.0003

Data Index: 589414 (C4 (Web Text))

Max Activating Token Index: 942

Text #9

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0831. Min Act: -0.0003

Data Index: 795701 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0834. Min Act: -0.0003

Data Index: 246197 (C4 (Web Text))

Max Activating Token Index: 394

Text #11

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0819. Min Act: -0.0003

Data Index: 1087606 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0823. Min Act: -0.0003

Data Index: 407498 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0793. Min Act: -0.0003

Data Index: 999435 (C4 (Web Text))

Max Activating Token Index: 354

Text #14

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0818. Min Act: -0.0003

Data Index: 643680 (C4 (Web Text))

Max Activating Token Index: 232

Text #15

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0795. Min Act: -0.0003

Data Index: 433568 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0804. Min Act: -0.0003

Data Index: 1350977 (C4 (Web Text))

Max Activating Token Index: 120

Text #17

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0763. Min Act: -0.0003

Data Index: 897029 (C4 (Web Text))

Max Activating Token Index: 549

Text #18

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0777. Min Act: -0.0003

Data Index: 596181 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0843. Min Act: -0.0003

Data Index: 997108 (C4 (Web Text))

Max Activating Token Index: 37