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

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

Neuron 3337 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: 1.6911. Min Range: -1.6911

Max Act: 1.6483. Min Act: -0.0000

Data Index: 960521 (C4 (Web Text))

Max Activating Token Index: 958

Text #1

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.6911. Min Act: -0.0000

Data Index: 575911 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.5721. Min Act: -0.0000

Data Index: 43211 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.5964. Min Act: -0.0000

Data Index: 878633 (C4 (Web Text))

Max Activating Token Index: 956

Text #4

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.5308. Min Act: -0.0000

Data Index: 159267 (C4 (Web Text))

Max Activating Token Index: 278

Text #5

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.5423. Min Act: -0.0000

Data Index: 1345039 (C4 (Web Text))

Max Activating Token Index: 679

Text #6

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.5253. Min Act: -0.0000

Data Index: 379403 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.5347. Min Act: -0.0000

Data Index: 571048 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.3860. Min Act: -0.0000

Data Index: 310785 (C4 (Web Text))

Max Activating Token Index: 197

Text #9

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.5041. Min Act: -0.0000

Data Index: 625377 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.4044. Min Act: -0.0000

Data Index: 861258 (C4 (Web Text))

Max Activating Token Index: 270

Text #11

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.3921. Min Act: -0.0000

Data Index: 1112678 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.3663. Min Act: -0.0000

Data Index: 1177392 (C4 (Web Text))

Max Activating Token Index: 548

Text #13

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.4865. Min Act: -0.0000

Data Index: 749082 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.2714. Min Act: -0.0000

Data Index: 823900 (C4 (Web Text))

Max Activating Token Index: 666

Text #15

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.3436. Min Act: -0.0000

Data Index: 1086647 (C4 (Web Text))

Max Activating Token Index: 1007

Text #16

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.3929. Min Act: -0.0000

Data Index: 1181858 (C4 (Web Text))

Max Activating Token Index: 791

Text #17

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.3249. Min Act: -0.0000

Data Index: 1212523 (C4 (Web Text))

Max Activating Token Index: 663

Text #18

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.3788. Min Act: -0.0000

Data Index: 836757 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.3449. Min Act: -0.0000

Data Index: 444541 (C4 (Web Text))

Max Activating Token Index: 277