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

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

Neuron 4627 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: 4.1824. Min Range: -4.1824

Max Act: 4.1824. Min Act: -0.0000

Data Index: 783163 (C4 (Web Text))

Max Activating Token Index: 356

Text #1

Max Range: 4.1824. Min Range: -4.1824

Max Act: 4.0298. Min Act: -0.0000

Data Index: 1143962 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 4.1824. Min Range: -4.1824

Max Act: 4.1792. Min Act: -0.0000

Data Index: 548559 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 4.1824. Min Range: -4.1824

Max Act: 4.0866. Min Act: -0.0000

Data Index: 1008955 (C4 (Web Text))

Max Activating Token Index: 441

Text #4

Max Range: 4.1824. Min Range: -4.1824

Max Act: 3.8639. Min Act: -0.0000

Data Index: 839458 (C4 (Web Text))

Max Activating Token Index: 110

Text #5

Max Range: 4.1824. Min Range: -4.1824

Max Act: 3.6034. Min Act: -0.0000

Data Index: 593852 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 4.1824. Min Range: -4.1824

Max Act: 3.9345. Min Act: -0.0000

Data Index: 370436 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 4.1824. Min Range: -4.1824

Max Act: 4.0193. Min Act: -0.0000

Data Index: 1012566 (C4 (Web Text))

Max Activating Token Index: 1019

Text #8

Max Range: 4.1824. Min Range: -4.1824

Max Act: 3.4998. Min Act: -0.0000

Data Index: 433162 (C4 (Web Text))

Max Activating Token Index: 131

Text #9

Max Range: 4.1824. Min Range: -4.1824

Max Act: 3.6407. Min Act: -0.0000

Data Index: 388845 (C4 (Web Text))

Max Activating Token Index: 562

Text #10

Max Range: 4.1824. Min Range: -4.1824

Max Act: 3.6400. Min Act: -0.0000

Data Index: 25468 (C4 (Web Text))

Max Activating Token Index: 433

Text #11

Max Range: 4.1824. Min Range: -4.1824

Max Act: 3.6203. Min Act: -0.0000

Data Index: 1063942 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 4.1824. Min Range: -4.1824

Max Act: 3.4972. Min Act: -0.0000

Data Index: 1201253 (C4 (Web Text))

Max Activating Token Index: 764

Text #13

Max Range: 4.1824. Min Range: -4.1824

Max Act: 3.4793. Min Act: -0.0000

Data Index: 593328 (C4 (Web Text))

Max Activating Token Index: 773

Text #14

Max Range: 4.1824. Min Range: -4.1824

Max Act: 3.4665. Min Act: -0.0000

Data Index: 51877 (C4 (Web Text))

Max Activating Token Index: 21

Text #15

Max Range: 4.1824. Min Range: -4.1824

Max Act: 3.3825. Min Act: -0.0000

Data Index: 1121412 (C4 (Web Text))

Max Activating Token Index: 438

Text #16

Max Range: 4.1824. Min Range: -4.1824

Max Act: 3.3301. Min Act: -0.0000

Data Index: 733454 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 4.1824. Min Range: -4.1824

Max Act: 3.2851. Min Act: -0.0000

Data Index: 1356111 (C4 (Web Text))

Max Activating Token Index: 906

Text #18

Max Range: 4.1824. Min Range: -4.1824

Max Act: 3.1235. Min Act: -0.0000

Data Index: 293200 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 4.1824. Min Range: -4.1824

Max Act: 3.4347. Min Act: -0.0000

Data Index: 773015 (C4 (Web Text))

Max Activating Token Index: 186