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

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

Neuron 1293 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8368. Min Range: -3.8368

Max Act: 3.8368. Min Act: -0.0000

Data Index: 617272 (C4 (Web Text))

Max Activating Token Index: 430

Text #1

Max Range: 3.8368. Min Range: -3.8368

Max Act: 3.7544. Min Act: -0.0000

Data Index: 93284 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 3.8368. Min Range: -3.8368

Max Act: 3.7272. Min Act: -0.0000

Data Index: 1069715 (C4 (Web Text))

Max Activating Token Index: 125

Text #3

Max Range: 3.8368. Min Range: -3.8368

Max Act: 3.8356. Min Act: -0.0000

Data Index: 520119 (C4 (Web Text))

Max Activating Token Index: 811

Text #4

Max Range: 3.8368. Min Range: -3.8368

Max Act: 3.5205. Min Act: -0.0000

Data Index: 396158 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 3.8368. Min Range: -3.8368

Max Act: 3.4627. Min Act: -0.0000

Data Index: 524485 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 3.8368. Min Range: -3.8368

Max Act: 3.0779. Min Act: -0.0000

Data Index: 1221086 (C4 (Web Text))

Max Activating Token Index: 767

Text #7

Max Range: 3.8368. Min Range: -3.8368

Max Act: 2.8638. Min Act: -0.0000

Data Index: 1247952 (C4 (Web Text))

Max Activating Token Index: 668

Text #8

Max Range: 3.8368. Min Range: -3.8368

Max Act: 2.9460. Min Act: -0.0000

Data Index: 663620 (C4 (Web Text))

Max Activating Token Index: 583

Text #9

Max Range: 3.8368. Min Range: -3.8368

Max Act: 2.8727. Min Act: -0.0000

Data Index: 564305 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 3.8368. Min Range: -3.8368

Max Act: 2.8129. Min Act: -0.0000

Data Index: 78975 (C4 (Web Text))

Max Activating Token Index: 936

Text #11

Max Range: 3.8368. Min Range: -3.8368

Max Act: 2.6569. Min Act: -0.0000

Data Index: 683127 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 3.8368. Min Range: -3.8368

Max Act: 2.6124. Min Act: -0.0000

Data Index: 666152 (C4 (Web Text))

Max Activating Token Index: 952

Text #13

Max Range: 3.8368. Min Range: -3.8368

Max Act: 2.4444. Min Act: -0.0000

Data Index: 529850 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 3.8368. Min Range: -3.8368

Max Act: 2.4304. Min Act: -0.0000

Data Index: 756892 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 3.8368. Min Range: -3.8368

Max Act: 2.4914. Min Act: -0.0000

Data Index: 1093586 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 3.8368. Min Range: -3.8368

Max Act: 2.4886. Min Act: -0.0000

Data Index: 1211298 (C4 (Web Text))

Max Activating Token Index: 588

Text #17

Max Range: 3.8368. Min Range: -3.8368

Max Act: 2.2333. Min Act: -0.0000

Data Index: 1102561 (C4 (Web Text))

Max Activating Token Index: 923

Text #18

Max Range: 3.8368. Min Range: -3.8368

Max Act: 2.4590. Min Act: -0.0000

Data Index: 460830 (C4 (Web Text))

Max Activating Token Index: 860

Text #19

Max Range: 3.8368. Min Range: -3.8368

Max Act: 2.3269. Min Act: -0.0000

Data Index: 1353899 (C4 (Web Text))

Max Activating Token Index: 68