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

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

Neuron 4558 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6106. Min Range: -0.6106

Max Act: 0.6106. Min Act: -0.0001

Data Index: 642420 (C4 (Web Text))

Max Activating Token Index: 284

Text #1

Max Range: 0.6106. Min Range: -0.6106

Max Act: 0.5274. Min Act: -0.0001

Data Index: 270931 (C4 (Web Text))

Max Activating Token Index: 326

Text #2

Max Range: 0.6106. Min Range: -0.6106

Max Act: 0.5019. Min Act: -0.0001

Data Index: 583283 (C4 (Web Text))

Max Activating Token Index: 604

Text #3

Max Range: 0.6106. Min Range: -0.6106

Max Act: 0.5431. Min Act: -0.0001

Data Index: 12598 (C4 (Web Text))

Max Activating Token Index: 363

Text #4

Max Range: 0.6106. Min Range: -0.6106

Max Act: 0.5357. Min Act: -0.0001

Data Index: 177513 (C4 (Web Text))

Max Activating Token Index: 746

Text #5

Max Range: 0.6106. Min Range: -0.6106

Max Act: 0.4646. Min Act: -0.0001

Data Index: 654092 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 0.6106. Min Range: -0.6106

Max Act: 0.4537. Min Act: -0.0001

Data Index: 786484 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 0.6106. Min Range: -0.6106

Max Act: 0.4896. Min Act: -0.0001

Data Index: 395449 (C4 (Web Text))

Max Activating Token Index: 553

Text #8

Max Range: 0.6106. Min Range: -0.6106

Max Act: 0.5504. Min Act: -0.0001

Data Index: 658846 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 0.6106. Min Range: -0.6106

Max Act: 0.4818. Min Act: -0.0001

Data Index: 961049 (C4 (Web Text))

Max Activating Token Index: 598

Text #10

Max Range: 0.6106. Min Range: -0.6106

Max Act: 0.4448. Min Act: -0.0001

Data Index: 854287 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 0.6106. Min Range: -0.6106

Max Act: 0.4805. Min Act: -0.0001

Data Index: 273295 (C4 (Web Text))

Max Activating Token Index: 228

Text #12

Max Range: 0.6106. Min Range: -0.6106

Max Act: 0.4168. Min Act: -0.0001

Data Index: 259901 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.6106. Min Range: -0.6106

Max Act: 0.4677. Min Act: -0.0001

Data Index: 616235 (C4 (Web Text))

Max Activating Token Index: 739

Text #14

Max Range: 0.6106. Min Range: -0.6106

Max Act: 0.4131. Min Act: -0.0001

Data Index: 1236152 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 0.6106. Min Range: -0.6106

Max Act: 0.4222. Min Act: -0.0001

Data Index: 612134 (C4 (Web Text))

Max Activating Token Index: 399

Text #16

Max Range: 0.6106. Min Range: -0.6106

Max Act: 0.4323. Min Act: -0.0001

Data Index: 268046 (C4 (Web Text))

Max Activating Token Index: 1012

Text #17

Max Range: 0.6106. Min Range: -0.6106

Max Act: 0.3825. Min Act: -0.0001

Data Index: 350069 (C4 (Web Text))

Max Activating Token Index: 510

Text #18

Max Range: 0.6106. Min Range: -0.6106

Max Act: 0.4244. Min Act: -0.0001

Data Index: 850771 (C4 (Web Text))

Max Activating Token Index: 816

Text #19

Max Range: 0.6106. Min Range: -0.6106

Max Act: 0.3815. Min Act: -0.0001

Data Index: 1269609 (C4 (Web Text))

Max Activating Token Index: 796