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

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

Neuron 321 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5493. Min Range: -4.5493

Max Act: 4.5493. Min Act: -0.0000

Data Index: 770280 (C4 (Web Text))

Max Activating Token Index: 445

Text #1

Max Range: 4.5493. Min Range: -4.5493

Max Act: 4.0800. Min Act: -0.0000

Data Index: 1254531 (C4 (Web Text))

Max Activating Token Index: 830

Text #2

Max Range: 4.5493. Min Range: -4.5493

Max Act: 4.2923. Min Act: -0.0000

Data Index: 963835 (C4 (Web Text))

Max Activating Token Index: 319

Text #3

Max Range: 4.5493. Min Range: -4.5493

Max Act: 3.3975. Min Act: -0.0000

Data Index: 284975 (C4 (Web Text))

Max Activating Token Index: 653

Text #4

Max Range: 4.5493. Min Range: -4.5493

Max Act: 3.4831. Min Act: -0.0000

Data Index: 176990 (C4 (Web Text))

Max Activating Token Index: 512

Text #5

Max Range: 4.5493. Min Range: -4.5493

Max Act: 3.5306. Min Act: -0.0001

Data Index: 1291196 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 4.5493. Min Range: -4.5493

Max Act: 2.4726. Min Act: -0.0000

Data Index: 119845 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 4.5493. Min Range: -4.5493

Max Act: 3.4804. Min Act: -0.0000

Data Index: 38841 (C4 (Web Text))

Max Activating Token Index: 1002

Text #8

Max Range: 4.5493. Min Range: -4.5493

Max Act: 3.0232. Min Act: -0.0000

Data Index: 1065279 (C4 (Web Text))

Max Activating Token Index: 647

Text #9

Max Range: 4.5493. Min Range: -4.5493

Max Act: 2.9952. Min Act: -0.0000

Data Index: 37200 (C4 (Web Text))

Max Activating Token Index: 992

Text #10

Max Range: 4.5493. Min Range: -4.5493

Max Act: 2.8737. Min Act: -0.0000

Data Index: 397974 (C4 (Web Text))

Max Activating Token Index: 742

Text #11

Max Range: 4.5493. Min Range: -4.5493

Max Act: 2.6363. Min Act: -0.0000

Data Index: 1269721 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 4.5493. Min Range: -4.5493

Max Act: 2.9325. Min Act: -0.0000

Data Index: 1142771 (C4 (Web Text))

Max Activating Token Index: 187

Text #13

Max Range: 4.5493. Min Range: -4.5493

Max Act: 2.4153. Min Act: -0.0000

Data Index: 1156527 (C4 (Web Text))

Max Activating Token Index: 154

Text #14

Max Range: 4.5493. Min Range: -4.5493

Max Act: 2.4561. Min Act: -0.0000

Data Index: 1099324 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 4.5493. Min Range: -4.5493

Max Act: 2.7001. Min Act: -0.0000

Data Index: 1004298 (C4 (Web Text))

Max Activating Token Index: 897

Text #16

Max Range: 4.5493. Min Range: -4.5493

Max Act: 2.5680. Min Act: -0.0000

Data Index: 191393 (C4 (Web Text))

Max Activating Token Index: 606

Text #17

Max Range: 4.5493. Min Range: -4.5493

Max Act: 2.5011. Min Act: -0.0000

Data Index: 184887 (C4 (Web Text))

Max Activating Token Index: 711

Text #18

Max Range: 4.5493. Min Range: -4.5493

Max Act: 2.2437. Min Act: -0.0000

Data Index: 564658 (C4 (Web Text))

Max Activating Token Index: 933

Text #19

Max Range: 4.5493. Min Range: -4.5493

Max Act: 2.3263. Min Act: -0.0001

Data Index: 9721 (C4 (Web Text))

Max Activating Token Index: 656