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

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

Neuron 1364 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6136. Min Range: -4.6136

Max Act: 4.6136. Min Act: -0.0000

Data Index: 1225003 (C4 (Web Text))

Max Activating Token Index: 397

Text #1

Max Range: 4.6136. Min Range: -4.6136

Max Act: 4.2608. Min Act: -0.0000

Data Index: 494742 (C4 (Web Text))

Max Activating Token Index: 867

Text #2

Max Range: 4.6136. Min Range: -4.6136

Max Act: 4.1946. Min Act: -0.0000

Data Index: 991428 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 4.6136. Min Range: -4.6136

Max Act: 4.1794. Min Act: -0.0000

Data Index: 1045302 (C4 (Web Text))

Max Activating Token Index: 363

Text #4

Max Range: 4.6136. Min Range: -4.6136

Max Act: 4.1500. Min Act: -0.0000

Data Index: 489550 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 4.6136. Min Range: -4.6136

Max Act: 4.0891. Min Act: -0.0000

Data Index: 424788 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 4.6136. Min Range: -4.6136

Max Act: 4.0900. Min Act: -0.0000

Data Index: 973677 (C4 (Web Text))

Max Activating Token Index: 1004

Text #7

Max Range: 4.6136. Min Range: -4.6136

Max Act: 4.0222. Min Act: -0.0000

Data Index: 39945 (C4 (Web Text))

Max Activating Token Index: 887

Text #8

Max Range: 4.6136. Min Range: -4.6136

Max Act: 4.0188. Min Act: -0.0000

Data Index: 1233575 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 4.6136. Min Range: -4.6136

Max Act: 4.0125. Min Act: -0.0000

Data Index: 634701 (C4 (Web Text))

Max Activating Token Index: 148

Text #10

Max Range: 4.6136. Min Range: -4.6136

Max Act: 3.9273. Min Act: -0.0000

Data Index: 383282 (C4 (Web Text))

Max Activating Token Index: 969

Text #11

Max Range: 4.6136. Min Range: -4.6136

Max Act: 3.7517. Min Act: -0.0000

Data Index: 103817 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 4.6136. Min Range: -4.6136

Max Act: 3.8890. Min Act: -0.0000

Data Index: 1154382 (C4 (Web Text))

Max Activating Token Index: 702

Text #13

Max Range: 4.6136. Min Range: -4.6136

Max Act: 3.8487. Min Act: -0.0000

Data Index: 891239 (C4 (Web Text))

Max Activating Token Index: 463

Text #14

Max Range: 4.6136. Min Range: -4.6136

Max Act: 3.8415. Min Act: 0.0000

Data Index: 284496 (C4 (Web Text))

Max Activating Token Index: 576

Text #15

Max Range: 4.6136. Min Range: -4.6136

Max Act: 3.6528. Min Act: -0.0000

Data Index: 426549 (C4 (Web Text))

Max Activating Token Index: 358

Text #16

Max Range: 4.6136. Min Range: -4.6136

Max Act: 3.8173. Min Act: -0.0000

Data Index: 831532 (C4 (Web Text))

Max Activating Token Index: 384

Text #17

Max Range: 4.6136. Min Range: -4.6136

Max Act: 3.6216. Min Act: -0.0000

Data Index: 253553 (C4 (Web Text))

Max Activating Token Index: 271

Text #18

Max Range: 4.6136. Min Range: -4.6136

Max Act: 3.7722. Min Act: -0.0000

Data Index: 234896 (C4 (Web Text))

Max Activating Token Index: 441

Text #19

Max Range: 4.6136. Min Range: -4.6136

Max Act: 3.7426. Min Act: 0.0000

Data Index: 442808 (C4 (Web Text))

Max Activating Token Index: 26