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

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

Neuron 2896 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: 1.5103. Min Range: -1.5103

Max Act: 1.4807. Min Act: -0.0000

Data Index: 984521 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 1.5103. Min Range: -1.5103

Max Act: 1.5103. Min Act: -0.0000

Data Index: 833386 (C4 (Web Text))

Max Activating Token Index: 616

Text #2

Max Range: 1.5103. Min Range: -1.5103

Max Act: 1.3770. Min Act: -0.0000

Data Index: 617046 (C4 (Web Text))

Max Activating Token Index: 965

Text #3

Max Range: 1.5103. Min Range: -1.5103

Max Act: 1.4419. Min Act: -0.0000

Data Index: 1051307 (C4 (Web Text))

Max Activating Token Index: 865

Text #4

Max Range: 1.5103. Min Range: -1.5103

Max Act: 1.3594. Min Act: -0.0000

Data Index: 1594 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 1.5103. Min Range: -1.5103

Max Act: 1.3261. Min Act: -0.0000

Data Index: 285177 (C4 (Web Text))

Max Activating Token Index: 300

Text #6

Max Range: 1.5103. Min Range: -1.5103

Max Act: 1.2835. Min Act: -0.0000

Data Index: 697147 (C4 (Web Text))

Max Activating Token Index: 510

Text #7

Max Range: 1.5103. Min Range: -1.5103

Max Act: 1.2850. Min Act: -0.0000

Data Index: 1200152 (C4 (Web Text))

Max Activating Token Index: 423

Text #8

Max Range: 1.5103. Min Range: -1.5103

Max Act: 1.2722. Min Act: -0.0000

Data Index: 284163 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 1.5103. Min Range: -1.5103

Max Act: 1.2021. Min Act: -0.0000

Data Index: 795053 (C4 (Web Text))

Max Activating Token Index: 337

Text #10

Max Range: 1.5103. Min Range: -1.5103

Max Act: 1.1963. Min Act: -0.0000

Data Index: 910051 (C4 (Web Text))

Max Activating Token Index: 910

Text #11

Max Range: 1.5103. Min Range: -1.5103

Max Act: 1.3088. Min Act: -0.0000

Data Index: 256428 (C4 (Web Text))

Max Activating Token Index: 271

Text #12

Max Range: 1.5103. Min Range: -1.5103

Max Act: 1.1911. Min Act: -0.0000

Data Index: 1010380 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 1.5103. Min Range: -1.5103

Max Act: 1.2458. Min Act: -0.0000

Data Index: 778349 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 1.5103. Min Range: -1.5103

Max Act: 1.2000. Min Act: -0.0000

Data Index: 101942 (C4 (Web Text))

Max Activating Token Index: 380

Text #15

Max Range: 1.5103. Min Range: -1.5103

Max Act: 1.1896. Min Act: -0.0000

Data Index: 1243057 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 1.5103. Min Range: -1.5103

Max Act: 1.1763. Min Act: -0.0000

Data Index: 232446 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 1.5103. Min Range: -1.5103

Max Act: 1.0590. Min Act: -0.0000

Data Index: 325462 (C4 (Web Text))

Max Activating Token Index: 269

Text #18

Max Range: 1.5103. Min Range: -1.5103

Max Act: 1.1245. Min Act: -0.0000

Data Index: 861748 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 1.5103. Min Range: -1.5103

Max Act: 1.1895. Min Act: -0.0000

Data Index: 1230203 (C4 (Web Text))

Max Activating Token Index: 614