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

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

Neuron 4751 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7183. Min Range: -0.7183

Max Act: 0.7174. Min Act: -0.0000

Data Index: 56466 (C4 (Web Text))

Max Activating Token Index: 644

Text #1

Max Range: 0.7183. Min Range: -0.7183

Max Act: 0.6841. Min Act: -0.0000

Data Index: 428740 (C4 (Web Text))

Max Activating Token Index: 864

Text #2

Max Range: 0.7183. Min Range: -0.7183

Max Act: 0.7183. Min Act: -0.0000

Data Index: 1295208 (C4 (Web Text))

Max Activating Token Index: 682

Text #3

Max Range: 0.7183. Min Range: -0.7183

Max Act: 0.7113. Min Act: -0.0000

Data Index: 194745 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 0.7183. Min Range: -0.7183

Max Act: 0.6751. Min Act: -0.0000

Data Index: 1099451 (C4 (Web Text))

Max Activating Token Index: 386

Text #5

Max Range: 0.7183. Min Range: -0.7183

Max Act: 0.6722. Min Act: -0.0000

Data Index: 1162469 (C4 (Web Text))

Max Activating Token Index: 366

Text #6

Max Range: 0.7183. Min Range: -0.7183

Max Act: 0.7129. Min Act: -0.0000

Data Index: 1000066 (C4 (Web Text))

Max Activating Token Index: 111

Text #7

Max Range: 0.7183. Min Range: -0.7183

Max Act: 0.6184. Min Act: -0.0000

Data Index: 964218 (C4 (Web Text))

Max Activating Token Index: 520

Text #8

Max Range: 0.7183. Min Range: -0.7183

Max Act: 0.6598. Min Act: -0.0000

Data Index: 173599 (C4 (Web Text))

Max Activating Token Index: 181

Text #9

Max Range: 0.7183. Min Range: -0.7183

Max Act: 0.6016. Min Act: -0.0000

Data Index: 965340 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 0.7183. Min Range: -0.7183

Max Act: 0.5988. Min Act: -0.0000

Data Index: 537784 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 0.7183. Min Range: -0.7183

Max Act: 0.5928. Min Act: -0.0000

Data Index: 620667 (C4 (Web Text))

Max Activating Token Index: 420

Text #12

Max Range: 0.7183. Min Range: -0.7183

Max Act: 0.5852. Min Act: -0.0000

Data Index: 605833 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 0.7183. Min Range: -0.7183

Max Act: 0.5758. Min Act: -0.0000

Data Index: 1086118 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 0.7183. Min Range: -0.7183

Max Act: 0.6083. Min Act: -0.0000

Data Index: 275559 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 0.7183. Min Range: -0.7183

Max Act: 0.5843. Min Act: -0.0000

Data Index: 395553 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 0.7183. Min Range: -0.7183

Max Act: 0.5974. Min Act: -0.0000

Data Index: 1046344 (C4 (Web Text))

Max Activating Token Index: 357

Text #17

Max Range: 0.7183. Min Range: -0.7183

Max Act: 0.5568. Min Act: -0.0000

Data Index: 564646 (C4 (Web Text))

Max Activating Token Index: 513

Text #18

Max Range: 0.7183. Min Range: -0.7183

Max Act: 0.5606. Min Act: -0.0000

Data Index: 1021746 (C4 (Web Text))

Max Activating Token Index: 892

Text #19

Max Range: 0.7183. Min Range: -0.7183

Max Act: 0.5483. Min Act: -0.0000

Data Index: 406374 (C4 (Web Text))

Max Activating Token Index: 963