Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 745 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.2588. Min Act: -0.0001

Data Index: 719368 (C4 (Web Text))

Max Activating Token Index: 464

Text #1

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.2366. Min Act: -0.0001

Data Index: 341628 (C4 (Web Text))

Max Activating Token Index: 386

Text #2

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.2205. Min Act: -0.0001

Data Index: 219589 (C4 (Web Text))

Max Activating Token Index: 965

Text #3

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1864. Min Act: -0.0000

Data Index: 942995 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1937. Min Act: -0.0001

Data Index: 921510 (C4 (Web Text))

Max Activating Token Index: 793

Text #5

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1983. Min Act: -0.0000

Data Index: 504124 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1907. Min Act: -0.0000

Data Index: 1266124 (C4 (Web Text))

Max Activating Token Index: 671

Text #7

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1908. Min Act: -0.0001

Data Index: 615977 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1876. Min Act: -0.0001

Data Index: 1094321 (C4 (Web Text))

Max Activating Token Index: 888

Text #9

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1932. Min Act: -0.0001

Data Index: 353443 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1805. Min Act: -0.0001

Data Index: 984636 (C4 (Web Text))

Max Activating Token Index: 713

Text #11

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1859. Min Act: -0.0001

Data Index: 54691 (C4 (Web Text))

Max Activating Token Index: 795

Text #12

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1787. Min Act: -0.0001

Data Index: 855310 (C4 (Web Text))

Max Activating Token Index: 873

Text #13

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1823. Min Act: -0.0000

Data Index: 592086 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1795. Min Act: -0.0000

Data Index: 160059 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1777. Min Act: -0.0000

Data Index: 942932 (C4 (Web Text))

Max Activating Token Index: 172

Text #16

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1790. Min Act: -0.0001

Data Index: 140152 (C4 (Web Text))

Max Activating Token Index: 455

Text #17

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1783. Min Act: -0.0001

Data Index: 212851 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1774. Min Act: -0.0000

Data Index: 663092 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1840. Min Act: -0.0001

Data Index: 640341 (C4 (Web Text))

Max Activating Token Index: 249