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

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

Neuron 4899 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9358. Min Range: -0.9358

Max Act: 0.8749. Min Act: -0.0000

Data Index: 434596 (C4 (Web Text))

Max Activating Token Index: 658

Text #1

Max Range: 0.9358. Min Range: -0.9358

Max Act: 0.9358. Min Act: -0.0000

Data Index: 228523 (C4 (Web Text))

Max Activating Token Index: 730

Text #2

Max Range: 0.9358. Min Range: -0.9358

Max Act: 0.7021. Min Act: -0.0000

Data Index: 437053 (C4 (Web Text))

Max Activating Token Index: 505

Text #3

Max Range: 0.9358. Min Range: -0.9358

Max Act: 0.6495. Min Act: -0.0000

Data Index: 631194 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 0.9358. Min Range: -0.9358

Max Act: 0.6402. Min Act: -0.0000

Data Index: 411950 (C4 (Web Text))

Max Activating Token Index: 820

Text #5

Max Range: 0.9358. Min Range: -0.9358

Max Act: 0.6784. Min Act: -0.0000

Data Index: 1022969 (C4 (Web Text))

Max Activating Token Index: 891

Text #6

Max Range: 0.9358. Min Range: -0.9358

Max Act: 0.5772. Min Act: -0.0000

Data Index: 1108572 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 0.9358. Min Range: -0.9358

Max Act: 0.5409. Min Act: -0.0000

Data Index: 941858 (C4 (Web Text))

Max Activating Token Index: 757

Text #8

Max Range: 0.9358. Min Range: -0.9358

Max Act: 0.5583. Min Act: -0.0000

Data Index: 63597 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 0.9358. Min Range: -0.9358

Max Act: 0.4994. Min Act: -0.0000

Data Index: 874175 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 0.9358. Min Range: -0.9358

Max Act: 0.5644. Min Act: -0.0000

Data Index: 198075 (C4 (Web Text))

Max Activating Token Index: 636

Text #11

Max Range: 0.9358. Min Range: -0.9358

Max Act: 0.5041. Min Act: -0.0000

Data Index: 1271386 (C4 (Web Text))

Max Activating Token Index: 388

Text #12

Max Range: 0.9358. Min Range: -0.9358

Max Act: 0.5378. Min Act: -0.0000

Data Index: 933570 (C4 (Web Text))

Max Activating Token Index: 553

Text #13

Max Range: 0.9358. Min Range: -0.9358

Max Act: 0.5295. Min Act: -0.0000

Data Index: 708640 (C4 (Web Text))

Max Activating Token Index: 993

Text #14

Max Range: 0.9358. Min Range: -0.9358

Max Act: 0.4006. Min Act: -0.0000

Data Index: 1129579 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 0.9358. Min Range: -0.9358

Max Act: 0.5201. Min Act: -0.0000

Data Index: 141751 (C4 (Web Text))

Max Activating Token Index: 377

Text #16

Max Range: 0.9358. Min Range: -0.9358

Max Act: 0.4963. Min Act: -0.0000

Data Index: 467016 (C4 (Web Text))

Max Activating Token Index: 564

Text #17

Max Range: 0.9358. Min Range: -0.9358

Max Act: 0.4706. Min Act: -0.0000

Data Index: 298675 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 0.9358. Min Range: -0.9358

Max Act: 0.4768. Min Act: -0.0000

Data Index: 292833 (C4 (Web Text))

Max Activating Token Index: 192

Text #19

Max Range: 0.9358. Min Range: -0.9358

Max Act: 0.5179. Min Act: -0.0000

Data Index: 100784 (C4 (Web Text))

Max Activating Token Index: 136