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

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

Neuron 1316 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7923. Min Range: -5.7923

Max Act: 5.7923. Min Act: -0.0001

Data Index: 225650 (C4 (Web Text))

Max Activating Token Index: 623

Text #1

Max Range: 5.7923. Min Range: -5.7923

Max Act: 5.6021. Min Act: -0.0001

Data Index: 732782 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 5.7923. Min Range: -5.7923

Max Act: 5.6106. Min Act: -0.0001

Data Index: 804565 (C4 (Web Text))

Max Activating Token Index: 209

Text #3

Max Range: 5.7923. Min Range: -5.7923

Max Act: 5.4001. Min Act: -0.0001

Data Index: 863078 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 5.7923. Min Range: -5.7923

Max Act: 5.2012. Min Act: -0.0001

Data Index: 719243 (C4 (Web Text))

Max Activating Token Index: 168

Text #5

Max Range: 5.7923. Min Range: -5.7923

Max Act: 5.0105. Min Act: -0.0001

Data Index: 949663 (C4 (Web Text))

Max Activating Token Index: 257

Text #6

Max Range: 5.7923. Min Range: -5.7923

Max Act: 4.8239. Min Act: -0.0001

Data Index: 435895 (C4 (Web Text))

Max Activating Token Index: 927

Text #7

Max Range: 5.7923. Min Range: -5.7923

Max Act: 4.6471. Min Act: -0.0001

Data Index: 1173478 (C4 (Web Text))

Max Activating Token Index: 402

Text #8

Max Range: 5.7923. Min Range: -5.7923

Max Act: 4.8970. Min Act: -0.0001

Data Index: 693920 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 5.7923. Min Range: -5.7923

Max Act: 4.8699. Min Act: -0.0001

Data Index: 1177521 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 5.7923. Min Range: -5.7923

Max Act: 4.6383. Min Act: -0.0001

Data Index: 1094908 (C4 (Web Text))

Max Activating Token Index: 307

Text #11

Max Range: 5.7923. Min Range: -5.7923

Max Act: 4.6321. Min Act: -0.0001

Data Index: 258304 (C4 (Web Text))

Max Activating Token Index: 533

Text #12

Max Range: 5.7923. Min Range: -5.7923

Max Act: 4.7825. Min Act: -0.0001

Data Index: 368551 (C4 (Web Text))

Max Activating Token Index: 628

Text #13

Max Range: 5.7923. Min Range: -5.7923

Max Act: 4.5990. Min Act: -0.0001

Data Index: 678562 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 5.7923. Min Range: -5.7923

Max Act: 4.9351. Min Act: -0.0001

Data Index: 972966 (C4 (Web Text))

Max Activating Token Index: 464

Text #15

Max Range: 5.7923. Min Range: -5.7923

Max Act: 4.4927. Min Act: -0.0001

Data Index: 1277652 (C4 (Web Text))

Max Activating Token Index: 647

Text #16

Max Range: 5.7923. Min Range: -5.7923

Max Act: 4.6604. Min Act: -0.0001

Data Index: 473469 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 5.7923. Min Range: -5.7923

Max Act: 4.4563. Min Act: -0.0001

Data Index: 125492 (C4 (Web Text))

Max Activating Token Index: 527

Text #18

Max Range: 5.7923. Min Range: -5.7923

Max Act: 4.6127. Min Act: -0.0001

Data Index: 1290293 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 5.7923. Min Range: -5.7923

Max Act: 4.7361. Min Act: -0.0001

Data Index: 691197 (C4 (Web Text))

Max Activating Token Index: 280