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

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

Neuron 2959 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: 1.2390. Min Range: -1.2390

Max Act: 1.2390. Min Act: -0.0000

Data Index: 605280 (C4 (Web Text))

Max Activating Token Index: 236

Text #1

Max Range: 1.2390. Min Range: -1.2390

Max Act: 1.1297. Min Act: -0.0000

Data Index: 966647 (C4 (Web Text))

Max Activating Token Index: 424

Text #2

Max Range: 1.2390. Min Range: -1.2390

Max Act: 1.1467. Min Act: 0.0002

Data Index: 287700 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 1.2390. Min Range: -1.2390

Max Act: 1.0271. Min Act: 0.0001

Data Index: 491342 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 1.2390. Min Range: -1.2390

Max Act: 1.1372. Min Act: -0.0000

Data Index: 1091728 (C4 (Web Text))

Max Activating Token Index: 741

Text #5

Max Range: 1.2390. Min Range: -1.2390

Max Act: 1.0212. Min Act: 0.0002

Data Index: 571660 (C4 (Web Text))

Max Activating Token Index: 490

Text #6

Max Range: 1.2390. Min Range: -1.2390

Max Act: 1.1029. Min Act: 0.0002

Data Index: 756854 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 1.2390. Min Range: -1.2390

Max Act: 1.1197. Min Act: -0.0000

Data Index: 369729 (C4 (Web Text))

Max Activating Token Index: 566

Text #8

Max Range: 1.2390. Min Range: -1.2390

Max Act: 0.9840. Min Act: 0.0001

Data Index: 590449 (C4 (Web Text))

Max Activating Token Index: 467

Text #9

Max Range: 1.2390. Min Range: -1.2390

Max Act: 1.0415. Min Act: 0.0002

Data Index: 914579 (C4 (Web Text))

Max Activating Token Index: 916

Text #10

Max Range: 1.2390. Min Range: -1.2390

Max Act: 0.9643. Min Act: -0.0000

Data Index: 13800 (C4 (Web Text))

Max Activating Token Index: 424

Text #11

Max Range: 1.2390. Min Range: -1.2390

Max Act: 0.9653. Min Act: -0.0000

Data Index: 1037135 (C4 (Web Text))

Max Activating Token Index: 393

Text #12

Max Range: 1.2390. Min Range: -1.2390

Max Act: 0.9980. Min Act: -0.0000

Data Index: 342363 (C4 (Web Text))

Max Activating Token Index: 145

Text #13

Max Range: 1.2390. Min Range: -1.2390

Max Act: 0.9018. Min Act: 0.0002

Data Index: 683683 (C4 (Web Text))

Max Activating Token Index: 779

Text #14

Max Range: 1.2390. Min Range: -1.2390

Max Act: 0.9436. Min Act: -0.0000

Data Index: 795363 (C4 (Web Text))

Max Activating Token Index: 753

Text #15

Max Range: 1.2390. Min Range: -1.2390

Max Act: 0.9714. Min Act: 0.0001

Data Index: 1226014 (C4 (Web Text))

Max Activating Token Index: 122

Text #16

Max Range: 1.2390. Min Range: -1.2390

Max Act: 0.9554. Min Act: -0.0000

Data Index: 1000932 (C4 (Web Text))

Max Activating Token Index: 593

Text #17

Max Range: 1.2390. Min Range: -1.2390

Max Act: 0.9307. Min Act: 0.0000

Data Index: 73576 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 1.2390. Min Range: -1.2390

Max Act: 0.8983. Min Act: -0.0000

Data Index: 758759 (C4 (Web Text))

Max Activating Token Index: 179

Text #19

Max Range: 1.2390. Min Range: -1.2390

Max Act: 0.9383. Min Act: -0.0000

Data Index: 902075 (C4 (Web Text))

Max Activating Token Index: 569