Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4047 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.9606. Min Range: -3.9606

Max Act: 3.9538. Min Act: -0.0000

Data Index: 178473 (C4 (Web Text))

Max Activating Token Index: 174

Text #1

Max Range: 3.9606. Min Range: -3.9606

Max Act: 3.5783. Min Act: -0.0000

Data Index: 1123957 (C4 (Web Text))

Max Activating Token Index: 985

Text #2

Max Range: 3.9606. Min Range: -3.9606

Max Act: 3.5557. Min Act: -0.0000

Data Index: 771657 (C4 (Web Text))

Max Activating Token Index: 699

Text #3

Max Range: 3.9606. Min Range: -3.9606

Max Act: 3.6849. Min Act: -0.0000

Data Index: 3556 (C4 (Web Text))

Max Activating Token Index: 369

Text #4

Max Range: 3.9606. Min Range: -3.9606

Max Act: 3.9606. Min Act: -0.0000

Data Index: 549991 (C4 (Web Text))

Max Activating Token Index: 202

Text #5

Max Range: 3.9606. Min Range: -3.9606

Max Act: 3.3922. Min Act: -0.0000

Data Index: 1354203 (C4 (Web Text))

Max Activating Token Index: 504

Text #6

Max Range: 3.9606. Min Range: -3.9606

Max Act: 3.2604. Min Act: -0.0000

Data Index: 444137 (C4 (Web Text))

Max Activating Token Index: 1007

Text #7

Max Range: 3.9606. Min Range: -3.9606

Max Act: 3.2155. Min Act: -0.0000

Data Index: 963152 (C4 (Web Text))

Max Activating Token Index: 303

Text #8

Max Range: 3.9606. Min Range: -3.9606

Max Act: 3.3455. Min Act: -0.0000

Data Index: 829632 (C4 (Web Text))

Max Activating Token Index: 494

Text #9

Max Range: 3.9606. Min Range: -3.9606

Max Act: 3.3697. Min Act: -0.0000

Data Index: 307979 (C4 (Web Text))

Max Activating Token Index: 658

Text #10

Max Range: 3.9606. Min Range: -3.9606

Max Act: 2.7495. Min Act: -0.0000

Data Index: 541301 (C4 (Web Text))

Max Activating Token Index: 262

Text #11

Max Range: 3.9606. Min Range: -3.9606

Max Act: 2.9004. Min Act: -0.0000

Data Index: 302359 (C4 (Web Text))

Max Activating Token Index: 530

Text #12

Max Range: 3.9606. Min Range: -3.9606

Max Act: 2.6410. Min Act: -0.0000

Data Index: 589205 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 3.9606. Min Range: -3.9606

Max Act: 2.6221. Min Act: -0.0000

Data Index: 344834 (C4 (Web Text))

Max Activating Token Index: 407

Text #14

Max Range: 3.9606. Min Range: -3.9606

Max Act: 2.5514. Min Act: -0.0000

Data Index: 1234433 (C4 (Web Text))

Max Activating Token Index: 783

Text #15

Max Range: 3.9606. Min Range: -3.9606

Max Act: 2.5042. Min Act: -0.0000

Data Index: 103980 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 3.9606. Min Range: -3.9606

Max Act: 2.6206. Min Act: -0.0000

Data Index: 1347263 (C4 (Web Text))

Max Activating Token Index: 527

Text #17

Max Range: 3.9606. Min Range: -3.9606

Max Act: 2.4298. Min Act: -0.0000

Data Index: 1014508 (C4 (Web Text))

Max Activating Token Index: 371

Text #18

Max Range: 3.9606. Min Range: -3.9606

Max Act: 2.5418. Min Act: -0.0000

Data Index: 1186117 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 3.9606. Min Range: -3.9606

Max Act: 2.3653. Min Act: -0.0000

Data Index: 574700 (C4 (Web Text))

Max Activating Token Index: 451