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

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

Neuron 1961 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4150. Min Range: -1.4150

Max Act: 1.4150. Min Act: -0.0000

Data Index: 939397 (C4 (Web Text))

Max Activating Token Index: 448

Text #1

Max Range: 1.4150. Min Range: -1.4150

Max Act: 1.1894. Min Act: -0.0000

Data Index: 727680 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 1.4150. Min Range: -1.4150

Max Act: 1.0407. Min Act: -0.0000

Data Index: 1359558 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 1.4150. Min Range: -1.4150

Max Act: 1.0315. Min Act: -0.0000

Data Index: 826439 (C4 (Web Text))

Max Activating Token Index: 318

Text #4

Max Range: 1.4150. Min Range: -1.4150

Max Act: 1.0043. Min Act: -0.0000

Data Index: 85369 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 1.4150. Min Range: -1.4150

Max Act: 1.0142. Min Act: -0.0000

Data Index: 799155 (C4 (Web Text))

Max Activating Token Index: 948

Text #6

Max Range: 1.4150. Min Range: -1.4150

Max Act: 0.8827. Min Act: -0.0000

Data Index: 1130629 (C4 (Web Text))

Max Activating Token Index: 531

Text #7

Max Range: 1.4150. Min Range: -1.4150

Max Act: 0.9660. Min Act: -0.0000

Data Index: 1171355 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 1.4150. Min Range: -1.4150

Max Act: 0.7896. Min Act: -0.0000

Data Index: 649723 (C4 (Web Text))

Max Activating Token Index: 479

Text #9

Max Range: 1.4150. Min Range: -1.4150

Max Act: 0.8239. Min Act: -0.0000

Data Index: 301209 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 1.4150. Min Range: -1.4150

Max Act: 0.8214. Min Act: -0.0000

Data Index: 283716 (C4 (Web Text))

Max Activating Token Index: 564

Text #11

Max Range: 1.4150. Min Range: -1.4150

Max Act: 0.7911. Min Act: -0.0000

Data Index: 1252263 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 1.4150. Min Range: -1.4150

Max Act: 0.8155. Min Act: -0.0000

Data Index: 237924 (C4 (Web Text))

Max Activating Token Index: 334

Text #13

Max Range: 1.4150. Min Range: -1.4150

Max Act: 0.6776. Min Act: -0.0000

Data Index: 158558 (C4 (Web Text))

Max Activating Token Index: 632

Text #14

Max Range: 1.4150. Min Range: -1.4150

Max Act: 0.7825. Min Act: -0.0000

Data Index: 717612 (C4 (Web Text))

Max Activating Token Index: 171

Text #15

Max Range: 1.4150. Min Range: -1.4150

Max Act: 0.7064. Min Act: -0.0000

Data Index: 1256774 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 1.4150. Min Range: -1.4150

Max Act: 0.7456. Min Act: -0.0000

Data Index: 505287 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 1.4150. Min Range: -1.4150

Max Act: 0.7341. Min Act: -0.0000

Data Index: 317476 (C4 (Web Text))

Max Activating Token Index: 426

Text #18

Max Range: 1.4150. Min Range: -1.4150

Max Act: 0.7767. Min Act: -0.0000

Data Index: 243908 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 1.4150. Min Range: -1.4150

Max Act: 0.7577. Min Act: -0.0000

Data Index: 464683 (C4 (Web Text))

Max Activating Token Index: 636