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

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

Neuron 2239 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: 4.9620. Min Range: -4.9620

Max Act: 4.9620. Min Act: -0.0000

Data Index: 61711 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 4.9620. Min Range: -4.9620

Max Act: 4.5412. Min Act: -0.0000

Data Index: 51760 (C4 (Web Text))

Max Activating Token Index: 668

Text #2

Max Range: 4.9620. Min Range: -4.9620

Max Act: 4.3301. Min Act: -0.0000

Data Index: 531493 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 4.9620. Min Range: -4.9620

Max Act: 3.8895. Min Act: -0.0000

Data Index: 394103 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 4.9620. Min Range: -4.9620

Max Act: 4.1993. Min Act: -0.0000

Data Index: 730263 (C4 (Web Text))

Max Activating Token Index: 562

Text #5

Max Range: 4.9620. Min Range: -4.9620

Max Act: 3.8292. Min Act: -0.0000

Data Index: 181078 (C4 (Web Text))

Max Activating Token Index: 309

Text #6

Max Range: 4.9620. Min Range: -4.9620

Max Act: 3.7474. Min Act: -0.0000

Data Index: 190444 (C4 (Web Text))

Max Activating Token Index: 484

Text #7

Max Range: 4.9620. Min Range: -4.9620

Max Act: 3.7318. Min Act: -0.0000

Data Index: 991056 (C4 (Web Text))

Max Activating Token Index: 146

Text #8

Max Range: 4.9620. Min Range: -4.9620

Max Act: 3.5821. Min Act: -0.0000

Data Index: 687224 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 4.9620. Min Range: -4.9620

Max Act: 3.5611. Min Act: -0.0000

Data Index: 631337 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 4.9620. Min Range: -4.9620

Max Act: 3.5377. Min Act: -0.0000

Data Index: 1260754 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 4.9620. Min Range: -4.9620

Max Act: 3.3450. Min Act: -0.0000

Data Index: 1123772 (C4 (Web Text))

Max Activating Token Index: 670

Text #12

Max Range: 4.9620. Min Range: -4.9620

Max Act: 3.6462. Min Act: -0.0000

Data Index: 705234 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 4.9620. Min Range: -4.9620

Max Act: 3.6391. Min Act: -0.0000

Data Index: 271998 (C4 (Web Text))

Max Activating Token Index: 494

Text #14

Max Range: 4.9620. Min Range: -4.9620

Max Act: 3.3919. Min Act: -0.0000

Data Index: 1036138 (C4 (Web Text))

Max Activating Token Index: 411

Text #15

Max Range: 4.9620. Min Range: -4.9620

Max Act: 3.0416. Min Act: -0.0000

Data Index: 813201 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 4.9620. Min Range: -4.9620

Max Act: 3.1677. Min Act: -0.0000

Data Index: 338866 (C4 (Web Text))

Max Activating Token Index: 382

Text #17

Max Range: 4.9620. Min Range: -4.9620

Max Act: 3.4366. Min Act: -0.0000

Data Index: 682151 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 4.9620. Min Range: -4.9620

Max Act: 3.4195. Min Act: -0.0000

Data Index: 1038069 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 4.9620. Min Range: -4.9620

Max Act: 3.2709. Min Act: -0.0000

Data Index: 269725 (C4 (Web Text))

Max Activating Token Index: 759