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

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

Neuron 4630 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.9084. Min Act: -0.0000

Data Index: 737309 (C4 (Web Text))

Max Activating Token Index: 264

Text #1

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.8493. Min Act: -0.0001

Data Index: 60873 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.8015. Min Act: -0.0000

Data Index: 951523 (C4 (Web Text))

Max Activating Token Index: 622

Text #3

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.6644. Min Act: -0.0000

Data Index: 30495 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.7939. Min Act: -0.0000

Data Index: 1133762 (C4 (Web Text))

Max Activating Token Index: 461

Text #5

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.7697. Min Act: -0.0000

Data Index: 779347 (C4 (Web Text))

Max Activating Token Index: 436

Text #6

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.8303. Min Act: -0.0001

Data Index: 640416 (C4 (Web Text))

Max Activating Token Index: 290

Text #7

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.7549. Min Act: -0.0000

Data Index: 11579 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.7219. Min Act: -0.0000

Data Index: 84986 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.7205. Min Act: -0.0000

Data Index: 376594 (C4 (Web Text))

Max Activating Token Index: 533

Text #10

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.7199. Min Act: -0.0000

Data Index: 116432 (C4 (Web Text))

Max Activating Token Index: 193

Text #11

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.6696. Min Act: -0.0000

Data Index: 78701 (C4 (Web Text))

Max Activating Token Index: 305

Text #12

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.7090. Min Act: -0.0000

Data Index: 881205 (C4 (Web Text))

Max Activating Token Index: 228

Text #13

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.6892. Min Act: -0.0000

Data Index: 403067 (C4 (Web Text))

Max Activating Token Index: 379

Text #14

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.7050. Min Act: -0.0000

Data Index: 919807 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.6264. Min Act: -0.0000

Data Index: 568976 (C4 (Web Text))

Max Activating Token Index: 746

Text #16

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.6729. Min Act: -0.0000

Data Index: 1160649 (C4 (Web Text))

Max Activating Token Index: 593

Text #17

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.6464. Min Act: -0.0000

Data Index: 1223417 (C4 (Web Text))

Max Activating Token Index: 503

Text #18

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.6763. Min Act: -0.0000

Data Index: 973177 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.6107. Min Act: -0.0000

Data Index: 1203670 (C4 (Web Text))

Max Activating Token Index: 223