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

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

Neuron 512 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0588. Min Act: -0.0002

Data Index: 988339 (C4 (Web Text))

Max Activating Token Index: 829

Text #1

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0581. Min Act: -0.0002

Data Index: 254482 (C4 (Web Text))

Max Activating Token Index: 971

Text #2

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0506. Min Act: -0.0002

Data Index: 47846 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0553. Min Act: -0.0002

Data Index: 610462 (C4 (Web Text))

Max Activating Token Index: 232

Text #4

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0504. Min Act: -0.0002

Data Index: 321077 (C4 (Web Text))

Max Activating Token Index: 483

Text #5

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0481. Min Act: -0.0002

Data Index: 591563 (C4 (Web Text))

Max Activating Token Index: 717

Text #6

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0416. Min Act: -0.0002

Data Index: 774842 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0450. Min Act: -0.0002

Data Index: 1067547 (C4 (Web Text))

Max Activating Token Index: 384

Text #8

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0452. Min Act: -0.0002

Data Index: 523040 (C4 (Web Text))

Max Activating Token Index: 645

Text #9

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0427. Min Act: -0.0002

Data Index: 584733 (C4 (Web Text))

Max Activating Token Index: 272

Text #10

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0430. Min Act: -0.0002

Data Index: 1265522 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0464. Min Act: -0.0002

Data Index: 559985 (C4 (Web Text))

Max Activating Token Index: 182

Text #12

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0388. Min Act: -0.0002

Data Index: 968456 (C4 (Web Text))

Max Activating Token Index: 694

Text #13

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0365. Min Act: -0.0002

Data Index: 1299555 (C4 (Web Text))

Max Activating Token Index: 625

Text #14

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0420. Min Act: -0.0002

Data Index: 1156897 (C4 (Web Text))

Max Activating Token Index: 542

Text #15

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0376. Min Act: -0.0002

Data Index: 228351 (C4 (Web Text))

Max Activating Token Index: 906

Text #16

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0361. Min Act: -0.0002

Data Index: 624435 (C4 (Web Text))

Max Activating Token Index: 870

Text #17

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0339. Min Act: -0.0002

Data Index: 761213 (C4 (Web Text))

Max Activating Token Index: 707

Text #18

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0392. Min Act: -0.0002

Data Index: 1222787 (C4 (Web Text))

Max Activating Token Index: 856

Text #19

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0392. Min Act: -0.0002

Data Index: 401209 (C4 (Web Text))

Max Activating Token Index: 507