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

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

Neuron 3275 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.7729. Min Act: -0.0000

Data Index: 235073 (C4 (Web Text))

Max Activating Token Index: 430

Text #1

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.5906. Min Act: -0.0000

Data Index: 412768 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.6213. Min Act: -0.0000

Data Index: 803044 (C4 (Web Text))

Max Activating Token Index: 77

Text #3

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.6256. Min Act: -0.0000

Data Index: 508458 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.5775. Min Act: -0.0000

Data Index: 1100170 (C4 (Web Text))

Max Activating Token Index: 1002

Text #5

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.5343. Min Act: -0.0000

Data Index: 970285 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.5004. Min Act: -0.0000

Data Index: 880852 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.5691. Min Act: -0.0000

Data Index: 677863 (C4 (Web Text))

Max Activating Token Index: 387

Text #8

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.5471. Min Act: -0.0000

Data Index: 194559 (C4 (Web Text))

Max Activating Token Index: 679

Text #9

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.5255. Min Act: -0.0000

Data Index: 376214 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.4891. Min Act: -0.0000

Data Index: 490795 (C4 (Web Text))

Max Activating Token Index: 168

Text #11

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.5466. Min Act: -0.0000

Data Index: 1173221 (C4 (Web Text))

Max Activating Token Index: 639

Text #12

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.5044. Min Act: -0.0000

Data Index: 1269586 (C4 (Web Text))

Max Activating Token Index: 663

Text #13

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.5058. Min Act: -0.0000

Data Index: 1001993 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.4757. Min Act: -0.0000

Data Index: 638278 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.4913. Min Act: -0.0000

Data Index: 1224617 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.4644. Min Act: -0.0000

Data Index: 774002 (C4 (Web Text))

Max Activating Token Index: 710

Text #17

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.4780. Min Act: -0.0000

Data Index: 813081 (C4 (Web Text))

Max Activating Token Index: 195

Text #18

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.4639. Min Act: -0.0000

Data Index: 848021 (C4 (Web Text))

Max Activating Token Index: 972

Text #19

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.4900. Min Act: -0.0000

Data Index: 806998 (C4 (Web Text))

Max Activating Token Index: 142