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

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

Neuron 2496 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: 3.9556. Min Range: -3.9556

Max Act: 3.8504. Min Act: -0.0000

Data Index: 663145 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 3.9556. Min Range: -3.9556

Max Act: 3.8180. Min Act: -0.0000

Data Index: 1540815 (Python Code)

Max Activating Token Index: 446

Text #2

Max Range: 3.9556. Min Range: -3.9556

Max Act: 3.9556. Min Act: -0.0000

Data Index: 178075 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 3.9556. Min Range: -3.9556

Max Act: 3.6419. Min Act: -0.0000

Data Index: 524181 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 3.9556. Min Range: -3.9556

Max Act: 3.7269. Min Act: -0.0000

Data Index: 422965 (C4 (Web Text))

Max Activating Token Index: 730

Text #5

Max Range: 3.9556. Min Range: -3.9556

Max Act: 3.5830. Min Act: -0.0000

Data Index: 1279106 (C4 (Web Text))

Max Activating Token Index: 220

Text #6

Max Range: 3.9556. Min Range: -3.9556

Max Act: 3.6011. Min Act: -0.0000

Data Index: 560474 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 3.9556. Min Range: -3.9556

Max Act: 3.5525. Min Act: -0.0000

Data Index: 622598 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 3.9556. Min Range: -3.9556

Max Act: 3.5113. Min Act: -0.0000

Data Index: 640968 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 3.9556. Min Range: -3.9556

Max Act: 3.4925. Min Act: -0.0000

Data Index: 312107 (C4 (Web Text))

Max Activating Token Index: 458

Text #10

Max Range: 3.9556. Min Range: -3.9556

Max Act: 3.4508. Min Act: -0.0000

Data Index: 311072 (C4 (Web Text))

Max Activating Token Index: 961

Text #11

Max Range: 3.9556. Min Range: -3.9556

Max Act: 3.3076. Min Act: -0.0000

Data Index: 933094 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 3.9556. Min Range: -3.9556

Max Act: 3.4122. Min Act: -0.0000

Data Index: 820345 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 3.9556. Min Range: -3.9556

Max Act: 3.2621. Min Act: -0.0000

Data Index: 264889 (C4 (Web Text))

Max Activating Token Index: 419

Text #14

Max Range: 3.9556. Min Range: -3.9556

Max Act: 3.2574. Min Act: -0.0000

Data Index: 1512893 (Python Code)

Max Activating Token Index: 252

Text #15

Max Range: 3.9556. Min Range: -3.9556

Max Act: 3.5988. Min Act: -0.0000

Data Index: 579787 (C4 (Web Text))

Max Activating Token Index: 996

Text #16

Max Range: 3.9556. Min Range: -3.9556

Max Act: 3.2596. Min Act: -0.0000

Data Index: 1336658 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 3.9556. Min Range: -3.9556

Max Act: 3.3701. Min Act: -0.0000

Data Index: 657660 (C4 (Web Text))

Max Activating Token Index: 915

Text #18

Max Range: 3.9556. Min Range: -3.9556

Max Act: 3.2410. Min Act: -0.0000

Data Index: 272275 (C4 (Web Text))

Max Activating Token Index: 1010

Text #19

Max Range: 3.9556. Min Range: -3.9556

Max Act: 3.3659. Min Act: -0.0000

Data Index: 21397 (C4 (Web Text))

Max Activating Token Index: 652