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

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

Neuron 1656 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3461. Min Range: -2.3461

Max Act: 2.3461. Min Act: -0.0000

Data Index: 49244 (C4 (Web Text))

Max Activating Token Index: 818

Text #1

Max Range: 2.3461. Min Range: -2.3461

Max Act: 2.3452. Min Act: -0.0000

Data Index: 518734 (C4 (Web Text))

Max Activating Token Index: 353

Text #2

Max Range: 2.3461. Min Range: -2.3461

Max Act: 2.0102. Min Act: -0.0000

Data Index: 585789 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 2.3461. Min Range: -2.3461

Max Act: 1.7200. Min Act: -0.0000

Data Index: 32260 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 2.3461. Min Range: -2.3461

Max Act: 1.9286. Min Act: -0.0000

Data Index: 1249998 (C4 (Web Text))

Max Activating Token Index: 259

Text #5

Max Range: 2.3461. Min Range: -2.3461

Max Act: 1.6718. Min Act: -0.0000

Data Index: 171718 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 2.3461. Min Range: -2.3461

Max Act: 1.7666. Min Act: -0.0000

Data Index: 657587 (C4 (Web Text))

Max Activating Token Index: 544

Text #7

Max Range: 2.3461. Min Range: -2.3461

Max Act: 1.6017. Min Act: -0.0000

Data Index: 1542000 (Python Code)

Max Activating Token Index: 504

Text #8

Max Range: 2.3461. Min Range: -2.3461

Max Act: 1.6619. Min Act: -0.0000

Data Index: 1455524 (Python Code)

Max Activating Token Index: 202

Text #9

Max Range: 2.3461. Min Range: -2.3461

Max Act: 1.4283. Min Act: -0.0000

Data Index: 1364962 (Python Code)

Max Activating Token Index: 457

Text #10

Max Range: 2.3461. Min Range: -2.3461

Max Act: 1.4929. Min Act: -0.0000

Data Index: 42905 (C4 (Web Text))

Max Activating Token Index: 798

Text #11

Max Range: 2.3461. Min Range: -2.3461

Max Act: 1.4087. Min Act: -0.0000

Data Index: 67049 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 2.3461. Min Range: -2.3461

Max Act: 1.4862. Min Act: -0.0000

Data Index: 395957 (C4 (Web Text))

Max Activating Token Index: 427

Text #13

Max Range: 2.3461. Min Range: -2.3461

Max Act: 1.4805. Min Act: -0.0000

Data Index: 923873 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 2.3461. Min Range: -2.3461

Max Act: 1.3856. Min Act: -0.0000

Data Index: 129298 (C4 (Web Text))

Max Activating Token Index: 298

Text #15

Max Range: 2.3461. Min Range: -2.3461

Max Act: 1.2951. Min Act: -0.0000

Data Index: 1171696 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 2.3461. Min Range: -2.3461

Max Act: 1.4429. Min Act: -0.0000

Data Index: 1295822 (C4 (Web Text))

Max Activating Token Index: 453

Text #17

Max Range: 2.3461. Min Range: -2.3461

Max Act: 1.4153. Min Act: -0.0000

Data Index: 441877 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 2.3461. Min Range: -2.3461

Max Act: 1.3374. Min Act: -0.0000

Data Index: 1171355 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 2.3461. Min Range: -2.3461

Max Act: 1.5018. Min Act: -0.0000

Data Index: 1591804 (Python Code)

Max Activating Token Index: 553