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

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

Neuron 920 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: 1.2561. Min Range: -1.2561

Max Act: 1.2561. Min Act: -0.0001

Data Index: 125903 (C4 (Web Text))

Max Activating Token Index: 345

Text #1

Max Range: 1.2561. Min Range: -1.2561

Max Act: 1.2121. Min Act: -0.0001

Data Index: 232186 (C4 (Web Text))

Max Activating Token Index: 321

Text #2

Max Range: 1.2561. Min Range: -1.2561

Max Act: 1.0724. Min Act: -0.0001

Data Index: 252002 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 1.2561. Min Range: -1.2561

Max Act: 1.0611. Min Act: -0.0001

Data Index: 866488 (C4 (Web Text))

Max Activating Token Index: 865

Text #4

Max Range: 1.2561. Min Range: -1.2561

Max Act: 1.0579. Min Act: -0.0001

Data Index: 975770 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 1.2561. Min Range: -1.2561

Max Act: 1.0032. Min Act: -0.0001

Data Index: 1144043 (C4 (Web Text))

Max Activating Token Index: 536

Text #6

Max Range: 1.2561. Min Range: -1.2561

Max Act: 1.0477. Min Act: -0.0001

Data Index: 794128 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 1.2561. Min Range: -1.2561

Max Act: 1.0322. Min Act: -0.0001

Data Index: 326449 (C4 (Web Text))

Max Activating Token Index: 715

Text #8

Max Range: 1.2561. Min Range: -1.2561

Max Act: 0.9639. Min Act: -0.0001

Data Index: 610644 (C4 (Web Text))

Max Activating Token Index: 477

Text #9

Max Range: 1.2561. Min Range: -1.2561

Max Act: 0.9228. Min Act: -0.0001

Data Index: 1284003 (C4 (Web Text))

Max Activating Token Index: 461

Text #10

Max Range: 1.2561. Min Range: -1.2561

Max Act: 0.9020. Min Act: -0.0001

Data Index: 1564439 (Python Code)

Max Activating Token Index: 726

Text #11

Max Range: 1.2561. Min Range: -1.2561

Max Act: 1.0047. Min Act: -0.0001

Data Index: 956358 (C4 (Web Text))

Max Activating Token Index: 323

Text #12

Max Range: 1.2561. Min Range: -1.2561

Max Act: 0.9203. Min Act: -0.0001

Data Index: 1108704 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 1.2561. Min Range: -1.2561

Max Act: 1.0257. Min Act: -0.0001

Data Index: 512749 (C4 (Web Text))

Max Activating Token Index: 243

Text #14

Max Range: 1.2561. Min Range: -1.2561

Max Act: 0.9686. Min Act: -0.0001

Data Index: 1069210 (C4 (Web Text))

Max Activating Token Index: 384

Text #15

Max Range: 1.2561. Min Range: -1.2561

Max Act: 0.9324. Min Act: -0.0001

Data Index: 306811 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 1.2561. Min Range: -1.2561

Max Act: 0.9867. Min Act: -0.0001

Data Index: 236023 (C4 (Web Text))

Max Activating Token Index: 580

Text #17

Max Range: 1.2561. Min Range: -1.2561

Max Act: 0.8563. Min Act: -0.0001

Data Index: 912253 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 1.2561. Min Range: -1.2561

Max Act: 0.9468. Min Act: -0.0001

Data Index: 360576 (C4 (Web Text))

Max Activating Token Index: 382

Text #19

Max Range: 1.2561. Min Range: -1.2561

Max Act: 0.8869. Min Act: -0.0001

Data Index: 652800 (C4 (Web Text))

Max Activating Token Index: 496