Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2159 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.6694. Min Act: -0.0001

Data Index: 1516910 (Python Code)

Max Activating Token Index: 740

Text #1

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.6050. Min Act: -0.0001

Data Index: 1400895 (Python Code)

Max Activating Token Index: 370

Text #2

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.5430. Min Act: -0.0001

Data Index: 1617929 (Python Code)

Max Activating Token Index: 197

Text #3

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.5543. Min Act: -0.0001

Data Index: 1361565 (Python Code)

Max Activating Token Index: 953

Text #4

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.5201. Min Act: -0.0001

Data Index: 1520978 (Python Code)

Max Activating Token Index: 237

Text #5

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.5302. Min Act: -0.0001

Data Index: 1547282 (Python Code)

Max Activating Token Index: 35

Text #6

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.5426. Min Act: -0.0001

Data Index: 1446078 (Python Code)

Max Activating Token Index: 243

Text #7

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.5306. Min Act: -0.0001

Data Index: 1449293 (Python Code)

Max Activating Token Index: 383

Text #8

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.5213. Min Act: -0.0001

Data Index: 1382799 (Python Code)

Max Activating Token Index: 342

Text #9

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.5226. Min Act: -0.0001

Data Index: 1363606 (Python Code)

Max Activating Token Index: 521

Text #10

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.5427. Min Act: -0.0001

Data Index: 1582945 (Python Code)

Max Activating Token Index: 22

Text #11

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.5386. Min Act: -0.0001

Data Index: 1377878 (Python Code)

Max Activating Token Index: 549

Text #12

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.5362. Min Act: -0.0001

Data Index: 1527758 (Python Code)

Max Activating Token Index: 543

Text #13

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.5349. Min Act: -0.0001

Data Index: 1621720 (Python Code)

Max Activating Token Index: 562

Text #14

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.5028. Min Act: -0.0001

Data Index: 1606482 (Python Code)

Max Activating Token Index: 410

Text #15

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.4986. Min Act: -0.0001

Data Index: 1466546 (Python Code)

Max Activating Token Index: 546

Text #16

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.5100. Min Act: -0.0001

Data Index: 1630871 (Python Code)

Max Activating Token Index: 211

Text #17

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.4870. Min Act: -0.0001

Data Index: 1398709 (Python Code)

Max Activating Token Index: 537

Text #18

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.5091. Min Act: -0.0001

Data Index: 1423264 (Python Code)

Max Activating Token Index: 288

Text #19

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.4877. Min Act: -0.0001

Data Index: 1529336 (Python Code)

Max Activating Token Index: 737