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

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

Neuron 3626 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4930. Min Range: -1.4930

Max Act: 1.4930. Min Act: -0.0000

Data Index: 541368 (C4 (Web Text))

Max Activating Token Index: 817

Text #1

Max Range: 1.4930. Min Range: -1.4930

Max Act: 1.4409. Min Act: -0.0000

Data Index: 1169078 (C4 (Web Text))

Max Activating Token Index: 763

Text #2

Max Range: 1.4930. Min Range: -1.4930

Max Act: 1.4471. Min Act: -0.0000

Data Index: 449544 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 1.4930. Min Range: -1.4930

Max Act: 1.2843. Min Act: -0.0000

Data Index: 1058283 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 1.4930. Min Range: -1.4930

Max Act: 1.2573. Min Act: -0.0000

Data Index: 1029519 (C4 (Web Text))

Max Activating Token Index: 426

Text #5

Max Range: 1.4930. Min Range: -1.4930

Max Act: 1.1708. Min Act: -0.0000

Data Index: 341162 (C4 (Web Text))

Max Activating Token Index: 632

Text #6

Max Range: 1.4930. Min Range: -1.4930

Max Act: 1.1731. Min Act: -0.0000

Data Index: 239230 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 1.4930. Min Range: -1.4930

Max Act: 1.1126. Min Act: -0.0000

Data Index: 829156 (C4 (Web Text))

Max Activating Token Index: 791

Text #8

Max Range: 1.4930. Min Range: -1.4930

Max Act: 1.1110. Min Act: -0.0000

Data Index: 1256743 (C4 (Web Text))

Max Activating Token Index: 361

Text #9

Max Range: 1.4930. Min Range: -1.4930

Max Act: 1.1621. Min Act: -0.0000

Data Index: 1053015 (C4 (Web Text))

Max Activating Token Index: 429

Text #10

Max Range: 1.4930. Min Range: -1.4930

Max Act: 1.0737. Min Act: -0.0000

Data Index: 32663 (C4 (Web Text))

Max Activating Token Index: 477

Text #11

Max Range: 1.4930. Min Range: -1.4930

Max Act: 1.0107. Min Act: -0.0000

Data Index: 681464 (C4 (Web Text))

Max Activating Token Index: 721

Text #12

Max Range: 1.4930. Min Range: -1.4930

Max Act: 0.9594. Min Act: -0.0000

Data Index: 1094435 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 1.4930. Min Range: -1.4930

Max Act: 1.0731. Min Act: -0.0000

Data Index: 969770 (C4 (Web Text))

Max Activating Token Index: 619

Text #14

Max Range: 1.4930. Min Range: -1.4930

Max Act: 1.0480. Min Act: -0.0000

Data Index: 493485 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 1.4930. Min Range: -1.4930

Max Act: 1.0463. Min Act: -0.0000

Data Index: 323813 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 1.4930. Min Range: -1.4930

Max Act: 1.0495. Min Act: -0.0000

Data Index: 1299531 (C4 (Web Text))

Max Activating Token Index: 553

Text #17

Max Range: 1.4930. Min Range: -1.4930

Max Act: 0.9886. Min Act: -0.0000

Data Index: 718289 (C4 (Web Text))

Max Activating Token Index: 202

Text #18

Max Range: 1.4930. Min Range: -1.4930

Max Act: 1.0209. Min Act: -0.0000

Data Index: 1016705 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 1.4930. Min Range: -1.4930

Max Act: 0.9131. Min Act: 0.0000

Data Index: 120280 (C4 (Web Text))

Max Activating Token Index: 343