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

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

Neuron 1498 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2918. Min Act: -0.0001

Data Index: 609712 (C4 (Web Text))

Max Activating Token Index: 927

Text #1

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2801. Min Act: -0.0001

Data Index: 718013 (C4 (Web Text))

Max Activating Token Index: 855

Text #2

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2916. Min Act: -0.0001

Data Index: 89510 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2824. Min Act: -0.0000

Data Index: 748053 (C4 (Web Text))

Max Activating Token Index: 308

Text #4

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2724. Min Act: -0.0001

Data Index: 733367 (C4 (Web Text))

Max Activating Token Index: 892

Text #5

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2675. Min Act: -0.0000

Data Index: 299777 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2534. Min Act: -0.0000

Data Index: 937956 (C4 (Web Text))

Max Activating Token Index: 413

Text #7

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2578. Min Act: -0.0001

Data Index: 1200527 (C4 (Web Text))

Max Activating Token Index: 703

Text #8

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2547. Min Act: -0.0001

Data Index: 767106 (C4 (Web Text))

Max Activating Token Index: 565

Text #9

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2544. Min Act: -0.0001

Data Index: 360735 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2270. Min Act: -0.0000

Data Index: 698259 (C4 (Web Text))

Max Activating Token Index: 171

Text #11

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2276. Min Act: -0.0001

Data Index: 1154982 (C4 (Web Text))

Max Activating Token Index: 182

Text #12

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2083. Min Act: -0.0001

Data Index: 1076221 (C4 (Web Text))

Max Activating Token Index: 283

Text #13

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2150. Min Act: -0.0001

Data Index: 955091 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.1972. Min Act: -0.0001

Data Index: 591736 (C4 (Web Text))

Max Activating Token Index: 247

Text #15

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2124. Min Act: -0.0001

Data Index: 1197121 (C4 (Web Text))

Max Activating Token Index: 395

Text #16

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2117. Min Act: -0.0001

Data Index: 67254 (C4 (Web Text))

Max Activating Token Index: 519

Text #17

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.1923. Min Act: -0.0000

Data Index: 1267051 (C4 (Web Text))

Max Activating Token Index: 162

Text #18

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2116. Min Act: -0.0001

Data Index: 786364 (C4 (Web Text))

Max Activating Token Index: 846

Text #19

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.1904. Min Act: -0.0001

Data Index: 764807 (C4 (Web Text))

Max Activating Token Index: 170