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

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

Neuron 3047 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: 2.8815. Min Range: -2.8815

Max Act: 2.8815. Min Act: -0.0000

Data Index: 764411 (C4 (Web Text))

Max Activating Token Index: 993

Text #1

Max Range: 2.8815. Min Range: -2.8815

Max Act: 2.1430. Min Act: -0.0000

Data Index: 583224 (C4 (Web Text))

Max Activating Token Index: 724

Text #2

Max Range: 2.8815. Min Range: -2.8815

Max Act: 1.8981. Min Act: -0.0000

Data Index: 200439 (C4 (Web Text))

Max Activating Token Index: 338

Text #3

Max Range: 2.8815. Min Range: -2.8815

Max Act: 1.8907. Min Act: -0.0000

Data Index: 1206742 (C4 (Web Text))

Max Activating Token Index: 270

Text #4

Max Range: 2.8815. Min Range: -2.8815

Max Act: 1.8668. Min Act: -0.0000

Data Index: 1317857 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 2.8815. Min Range: -2.8815

Max Act: 1.8061. Min Act: -0.0000

Data Index: 352660 (C4 (Web Text))

Max Activating Token Index: 415

Text #6

Max Range: 2.8815. Min Range: -2.8815

Max Act: 1.6058. Min Act: -0.0000

Data Index: 1157122 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 2.8815. Min Range: -2.8815

Max Act: 1.7248. Min Act: -0.0000

Data Index: 963338 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 2.8815. Min Range: -2.8815

Max Act: 1.5850. Min Act: -0.0000

Data Index: 527242 (C4 (Web Text))

Max Activating Token Index: 896

Text #9

Max Range: 2.8815. Min Range: -2.8815

Max Act: 1.5390. Min Act: -0.0000

Data Index: 397179 (C4 (Web Text))

Max Activating Token Index: 438

Text #10

Max Range: 2.8815. Min Range: -2.8815

Max Act: 1.4573. Min Act: -0.0000

Data Index: 887896 (C4 (Web Text))

Max Activating Token Index: 102

Text #11

Max Range: 2.8815. Min Range: -2.8815

Max Act: 1.5386. Min Act: -0.0000

Data Index: 688724 (C4 (Web Text))

Max Activating Token Index: 598

Text #12

Max Range: 2.8815. Min Range: -2.8815

Max Act: 1.5352. Min Act: -0.0000

Data Index: 1005678 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 2.8815. Min Range: -2.8815

Max Act: 1.5058. Min Act: -0.0000

Data Index: 247405 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 2.8815. Min Range: -2.8815

Max Act: 1.2790. Min Act: -0.0000

Data Index: 47583 (C4 (Web Text))

Max Activating Token Index: 881

Text #15

Max Range: 2.8815. Min Range: -2.8815

Max Act: 1.5026. Min Act: -0.0000

Data Index: 265039 (C4 (Web Text))

Max Activating Token Index: 800

Text #16

Max Range: 2.8815. Min Range: -2.8815

Max Act: 1.4678. Min Act: -0.0000

Data Index: 103099 (C4 (Web Text))

Max Activating Token Index: 873

Text #17

Max Range: 2.8815. Min Range: -2.8815

Max Act: 1.3771. Min Act: -0.0000

Data Index: 440637 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 2.8815. Min Range: -2.8815

Max Act: 1.3302. Min Act: -0.0000

Data Index: 651914 (C4 (Web Text))

Max Activating Token Index: 632

Text #19

Max Range: 2.8815. Min Range: -2.8815

Max Act: 1.3170. Min Act: -0.0000

Data Index: 711644 (C4 (Web Text))

Max Activating Token Index: 464