Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3266 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.9312. Min Range: -3.9312

Max Act: 3.9312. Min Act: -0.0000

Data Index: 1029593 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 3.9312. Min Range: -3.9312

Max Act: 2.8855. Min Act: -0.0000

Data Index: 1201046 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 3.9312. Min Range: -3.9312

Max Act: 2.9972. Min Act: -0.0000

Data Index: 413611 (C4 (Web Text))

Max Activating Token Index: 670

Text #3

Max Range: 3.9312. Min Range: -3.9312

Max Act: 2.7405. Min Act: -0.0000

Data Index: 1210289 (C4 (Web Text))

Max Activating Token Index: 600

Text #4

Max Range: 3.9312. Min Range: -3.9312

Max Act: 2.6110. Min Act: -0.0000

Data Index: 3194 (C4 (Web Text))

Max Activating Token Index: 47

Text #5

Max Range: 3.9312. Min Range: -3.9312

Max Act: 2.6890. Min Act: -0.0000

Data Index: 575655 (C4 (Web Text))

Max Activating Token Index: 747

Text #6

Max Range: 3.9312. Min Range: -3.9312

Max Act: 2.5496. Min Act: -0.0000

Data Index: 548439 (C4 (Web Text))

Max Activating Token Index: 829

Text #7

Max Range: 3.9312. Min Range: -3.9312

Max Act: 2.3168. Min Act: -0.0000

Data Index: 834564 (C4 (Web Text))

Max Activating Token Index: 973

Text #8

Max Range: 3.9312. Min Range: -3.9312

Max Act: 2.2387. Min Act: -0.0000

Data Index: 1111048 (C4 (Web Text))

Max Activating Token Index: 526

Text #9

Max Range: 3.9312. Min Range: -3.9312

Max Act: 2.1108. Min Act: -0.0000

Data Index: 61715 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 3.9312. Min Range: -3.9312

Max Act: 2.3524. Min Act: -0.0000

Data Index: 1239661 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 3.9312. Min Range: -3.9312

Max Act: 2.3350. Min Act: -0.0000

Data Index: 170003 (C4 (Web Text))

Max Activating Token Index: 788

Text #12

Max Range: 3.9312. Min Range: -3.9312

Max Act: 2.1784. Min Act: -0.0000

Data Index: 519826 (C4 (Web Text))

Max Activating Token Index: 719

Text #13

Max Range: 3.9312. Min Range: -3.9312

Max Act: 2.1564. Min Act: -0.0000

Data Index: 580458 (C4 (Web Text))

Max Activating Token Index: 278

Text #14

Max Range: 3.9312. Min Range: -3.9312

Max Act: 2.1476. Min Act: -0.0000

Data Index: 51116 (C4 (Web Text))

Max Activating Token Index: 709

Text #15

Max Range: 3.9312. Min Range: -3.9312

Max Act: 1.9977. Min Act: -0.0000

Data Index: 467142 (C4 (Web Text))

Max Activating Token Index: 769

Text #16

Max Range: 3.9312. Min Range: -3.9312

Max Act: 2.0744. Min Act: -0.0000

Data Index: 829059 (C4 (Web Text))

Max Activating Token Index: 460

Text #17

Max Range: 3.9312. Min Range: -3.9312

Max Act: 1.8644. Min Act: -0.0000

Data Index: 241204 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 3.9312. Min Range: -3.9312

Max Act: 2.1802. Min Act: -0.0000

Data Index: 1016419 (C4 (Web Text))

Max Activating Token Index: 853

Text #19

Max Range: 3.9312. Min Range: -3.9312

Max Act: 2.0736. Min Act: -0.0000

Data Index: 134617 (C4 (Web Text))

Max Activating Token Index: 597